will-taggart commited on
Commit
6f0d79d
·
verified ·
1 Parent(s): 8820edc

Describe native macOS workflow and refine research context

Browse files
TECHNICAL_REPORT.md CHANGED
@@ -3,32 +3,42 @@
3
  **William Taggart**
4
  Modern and Classical Languages and Literatures, Virginia Tech
5
  Email: wtaggart@vt.edu
6
- **Technical report · November 13, 2026 · Revision 0.2**
7
 
8
  ## Abstract
9
 
10
- AFFECTOR-ARC is an experimental command-line system for rewriting text under a user-defined emotional trajectory. It runs a frozen Qwen3.5-0.8B model on an NVIDIA GPU and changes selected internal activations during generation. A trajectory specifies valence, inward/outward emotional orientation, and intensity across normalized document position. Small sets of contrasting English passages establish three activation directions at each selected transformer layer. At inference time, the requested coordinates determine a weighted displacement, scaled relative to the current hidden-state magnitude, smoothed across decoding steps, and constrained by an RMS budget. Paired hooks apply this displacement to both the feed-forward input and its residual path. Document rewriting combines these interventions with four editing styles, sentence-aware segmentation, bounded generation, and incremental reporting. This report derives the mechanism from its implemented operations and distinguishes numerical controls from emotional outcomes. CPU policy tests pass; the current revision still requires CUDA validation. No measured claim of emotional accuracy, semantic preservation, or multilingual effectiveness is made.
11
 
12
  ## Purpose and Research Context
13
 
14
- AFFECTOR-ARC investigates how a prescribed emotional progression can influence a document rewrite on an allocated GPU. A user supplies a UTF-8 text and an ordered sequence of valence, inward/outward emotional orientation, and intensity coordinates. The runner maps document positions to that sequence and converts the sampled coordinates into activation displacements during generation. Here, geometry means a path through a three-dimensional coordinate space, with layer settings and optional calibration matrices. It expresses a desired progression rather than a surface reconstructed from text or a constraint applied directly to individual words.
15
 
16
- The intervention acts on the numerical hidden states used to predict successive tokens while the model's stored parameters remain fixed. This approach builds on contrastive activation steering: Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples ([Turner et al., 2023](https://arxiv.org/abs/2308.10248v1); [Panickssery et al., 2024](https://arxiv.org/abs/2312.06681v4)). AFFECTOR-ARC uses small sets of contrasting passages to establish emotional directions at selected layers, then applies coordinate-dependent displacements as each passage is rewritten. The contribution is an inspectable implementation of this mapping and its operational controls, not a claim that the emotional coordinates uniquely determine a continuation.
 
 
17
 
18
  ![Document workspace displaying an existing Little Red Riding Hood input and rewrite.](paper/figures/screenshot-02.png)
19
 
20
  *Document workspace displaying an existing Little Red Riding Hood input and rewrite.*
21
 
22
- Research connecting model emotion spaces with human valence/arousal judgments provides motivation for coordinate-based experimentation. Wu and colleagues report concept-based steering across linguistic-cultural settings ([Wu et al., 2025](https://arxiv.org/abs/2506.13978v1)), while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality ([Diallo et al., 2026](https://arxiv.org/abs/2601.21505v1)). Their findings make human interpretation central to evaluation, but they do not calibrate the present inward/outward axis or RMS-scaled settings. A text's emotional reading, its requested coordinates, and the model's hidden states remain distinct objects linked by an experimental calibration.
23
 
24
- That distinction matters when selecting layers and combining axes. Shu and colleagues find uneven causal organization across emotion categories in sparse-feature interventions for recognition ([Shu et al., 2026](https://arxiv.org/abs/2604.25866v3)); Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers ([Wang et al., 2026](https://arxiv.org/abs/2609.22135v1)). Ha and colleagues likewise find that supportive-empathy directions are only partially separable ([Ha et al., 2026](https://arxiv.org/abs/2609.15654v1)). Automated vector extraction and context-dependent strength offer further approaches to calibration and control ([Cui et al., 2025](https://arxiv.org/abs/2509.22739v3); [Ferrando et al., 2025](https://arxiv.org/abs/2512.03661v2)). These studies motivate layer sweeps, cross-axis tests, and adaptive controls, while the present runner uses an explicit coordinate mixture with user-selected settings.
25
 
26
- Generation limits and failure reporting are part of the same research problem. E-STEER reports non-monotonic effects of emotional interventions across several tasks ([Sun et al., 2026](https://arxiv.org/abs/2604.00005v1)), and Jeong observes both emotional changes and degeneration in small models ([Jeong, 2026](https://arxiv.org/abs/2604.04064v1)). Stronger settings therefore cannot be assumed to improve transfer. The runner offers a rewrite mode that processes a document in chunks and records attempts and failures, and a smoke mode with five controlled generation conditions for checking intervention and cleanup behavior. Its scope is the command-line CUDA computation illustrated alongside the desktop client's workspaces; the runner itself supplies neither a hosted service, conversational history, nor automatic emotional scoring.
27
 
28
- This operational scope determines the evidence needed to assess the system. SteerScope evaluates efficacy together with side effects, generalization, and dependence on steering data, and finds no general advantage of activation methods over prompt steering in its tested trade-offs ([Yang et al., 2026](https://arxiv.org/abs/2610.07722v1)). AFFECTOR-ARC therefore requires prompt-only and unsteered baselines, blinded emotional and quality ratings, content-change assessment, and complete reporting of repetition and truncation. The report documents the implemented mechanism and engineering checks; these broader comparisons and an empirically established operating range remain future work.
29
 
30
  ## Runtime and data flow
31
 
 
 
 
 
 
 
 
 
32
  The runner loads `Qwen/Qwen3.5-0.8B` at revision `2fc06364715b967f1860aea9cf38778875588b17`. The implementation uses `Qwen3_5ForConditionalGeneration`, its text decoder layers, float32 computation, eager attention, and the first process-visible CUDA device. It checks for 24 decoder layers; the geometry and calibration code assume hidden width 1,024. The backbone is in evaluation mode, its parameters have gradients disabled, and calibration and generation run without gradient tracking.
33
 
34
  ![Connection workspace with SSH settings and the Slurm GPU resource request. The client is offline in this capture.](paper/figures/screenshot-01.png)
@@ -248,6 +258,8 @@ Successful generation records include stopping reason, token count, elapsed time
248
 
249
  JSON writes use temporary-file replacement. The companion text file is written normally and may be incomplete if interrupted during that write. Reports are incremental records, not automatic resume checkpoints: rerunning starts over and overwrites the selected output paths. Use a distinct output filename for each experiment. Reports contain the input text and should be treated as document-bearing artifacts.
250
 
 
 
251
  ## Engineering checks and evidence
252
 
253
  Smoke mode is the default and operates on one supplied passage. It runs baseline, zero-strength, positive-valence, negative-valence, and restored-baseline conditions. Positive and negative conditions use coefficient vectors $(0.8,0,0)$ and $(-0.8,0,0)$. The third coordinate zero corresponds to intensity 0.5.
@@ -258,9 +270,13 @@ Smoke mode defaults to the original 128-token allowance and 600-second time thre
258
 
259
  For the November 13 revision, seven CPU policy tests passed, Python and shell syntax were checked, and CLI loading was verified. Tests cover such behavior as unchanged requested controls, paragraph allowance accounting, draft retention, sentence cleanup, and continuing after a failed chunk. They do not execute the CUDA model. The current revision has not yet been run on an ARC GPU. A successful GPU run was reported for an earlier revision on November 12; it is historical evidence, not validation of the current code.
260
 
 
 
261
  ## Reproduction
262
 
263
- Inside a suitable ARC GPU allocation, from a fresh repository copy:
 
 
264
 
265
  ```bash
266
  bash setup.sh
@@ -298,8 +314,9 @@ Changing to a larger model requires new architecture validation, basis calibrati
298
 
299
  ## Implementation sources
300
 
301
- This report describes the repository's executable operations rather than relying on another application's interface or documentation.
302
 
 
303
  - [CUDA runner and smoke protocol](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py)
304
  - [Document transformation and incremental output](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/document_run.py)
305
  - [Calibration, displacement math, hooks, and decoding](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/engine/steering.py)
 
3
  **William Taggart**
4
  Modern and Classical Languages and Literatures, Virginia Tech
5
  Email: wtaggart@vt.edu
6
+ **Technical report · November 14, 2026 · Revision 0.3**
7
 
8
  ## Abstract
9
 
10
+ AFFECTOR-ARC is an experimental text-rewriting system with a native macOS application and a command-line CUDA runner. The desktop application manages documents, emotional geometries, SSH connections, Slurm GPU jobs, and downloaded results; the runner executes a frozen Qwen3.5-0.8B model on an allocated ARC GPU. A trajectory specifies valence, inward/outward emotional orientation, and intensity across normalized document position. Contrasting English passages establish three activation directions at each selected transformer layer. During generation, trajectory coordinates determine a displacement scaled to the hidden-state magnitude, smoothed across decoding steps, and constrained by an RMS budget. Paired hooks apply it to the feed-forward input and residual path. Four editing styles, sentence-aware segmentation, bounded generation, and incremental reports make the intervention available within a document workflow. This report describes both interfaces and derives the steering mechanism, while distinguishing implementation checks from evidence of emotional effectiveness. Earlier desktop GPU runs and CPU policy tests are documented separately; they do not validate every subsequent runner revision or establish emotional accuracy, semantic preservation, or multilingual effectiveness.
11
 
12
  ## Purpose and Research Context
13
 
14
+ AFFECTOR-ARC investigates whether a writer can guide the emotional progression of a document by specifying a trajectory and intervening in a language model's internal computation. The practical aim is to make that experiment usable across a complete rewrite: the writer selects a text, supplies an emotional geometry, adjusts the intervention, and inspects the resulting passages and diagnostics. A native macOS application brings these activities into a workspace, while SSH and Slurm connect that workspace to a GPU allocation on Virginia Tech ARC. A command-line runner exposes the computation separately for scripted experiments and reproducible execution.
15
 
16
+ The geometry gives this workflow a common representation. It is an ordered path through valence, inward/outward emotional orientation, and intensity, accompanied by layer settings and optional calibration matrices. Sampling the path at successive document positions supplies the coordinates used during rewriting. Those coordinates become displacements of the model's hidden states, so the desired progression acts on the computation that produces tokens rather than prescribing particular words. The model's stored parameters remain fixed throughout.
17
+
18
+ This mechanism builds on contrastive activation steering. Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples ([Turner et al., 2023](https://arxiv.org/abs/2308.10248v1); [Panickssery et al., 2024](https://arxiv.org/abs/2312.06681v4)). AFFECTOR-ARC applies the same broad principle to small sets of emotionally contrasting passages, then mixes the resulting directions according to the requested trajectory. The central research question is how reliably this mapping can influence a sustained rewrite, given that a numerical displacement need not produce a unique or consistent emotional interpretation.
19
 
20
  ![Document workspace displaying an existing Little Red Riding Hood input and rewrite.](paper/figures/screenshot-02.png)
21
 
22
  *Document workspace displaying an existing Little Red Riding Hood input and rewrite.*
23
 
24
+ That question connects the implementation to research on the relation between model representations and human judgments. Wu and colleagues study concept-based emotional steering across linguistic-cultural settings, while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality ([Wu et al., 2025](https://arxiv.org/abs/2506.13978v1); [Diallo et al., 2026](https://arxiv.org/abs/2601.21505v1)). These studies motivate coordinate-based experiments whose outcomes are judged through readers' interpretations. They do not, however, establish the validity of this system's inward/outward axis or calibrate its RMS-scaled controls. The requested trajectory, the activation displacement, and the emotion perceived in the output must therefore be evaluated as related but distinct quantities.
25
 
26
+ The reliability of that relationship also depends on where and how the intervention is applied. Shu and colleagues find uneven causal organization across emotion categories, and Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers ([Shu et al., 2026](https://arxiv.org/abs/2604.25866v3); [Wang et al., 2026](https://arxiv.org/abs/2609.22135v1)). Ha and colleagues' finding that supportive-empathy directions are only partially separable further cautions against treating emotional axes as independent controls ([Ha et al., 2026](https://arxiv.org/abs/2609.15654v1)). Automated vector extraction and context-dependent strength offer approaches to these calibration problems ([Cui et al., 2025](https://arxiv.org/abs/2509.22739v3); [Ferrando et al., 2025](https://arxiv.org/abs/2512.03661v2)). AFFECTOR-ARC makes layer weights and axis mixtures explicit so that such questions can be investigated, although its current runner uses user-selected settings rather than an adaptive emotional-feedback controller.
27
 
28
+ Applying those settings across a document makes generation stability part of the same problem. E-STEER reports non-monotonic effects of emotional interventions, and Jeong observes both emotional changes and degeneration in small models ([Sun et al., 2026](https://arxiv.org/abs/2604.00005v1); [Jeong, 2026](https://arxiv.org/abs/2604.04064v1)). A stronger displacement can thus disrupt a rewrite without bringing it closer to the intended trajectory. The system addresses the operational consequences through bounded generation, repetition checks, passage-level failure records, and a desktop workflow for reviewing jobs and results. These safeguards preserve an inspectable experiment; they do not establish that a completed rewrite meets its emotional target.
29
 
30
+ Evaluation must consequently consider emotional alignment together with fluency, content change, and failure rates. SteerScope examines efficacy, side effects, generalization, and dependence on steering data, finding no general advantage over prompt steering in its tested trade-offs ([Yang et al., 2026](https://arxiv.org/abs/2610.07722v1)). For AFFECTOR-ARC, this motivates comparisons with prompt-only and unsteered rewriting, blinded emotional and quality ratings, and complete reporting of retained originals, repetition, and truncation. The scope of this report is the desktop-to-cluster workflow and the implemented steering procedure, including their engineering checks. Establishing emotional effectiveness and a reliable operating range remains an empirical task.
31
 
32
  ## Runtime and data flow
33
 
34
+ ### Native macOS client and remote execution
35
+
36
+ The native SwiftUI application is distributed on Hugging Face for Apple Silicon Macs running macOS 15 or later. Its connection workspace configures SSH access and the Slurm resource request. The document workspace holds the input and generated text; the shape and weights workspace supports importing, converting, and editing geometries and intervention settings. Jobs and results controls expose remote progress, diagnostics, and output downloads. The application also manages Hugging Face source updates and submits GPU-environment setup through Slurm.
37
+
38
+ The Mac serves as the client: lightweight SSH requests manage files and jobs, while model setup and execution run in requested GPU allocations. The bundled Python remote agent handles requests over SSH without a persistent listening server. The desktop interface and the command-line runner are separately versioned components, so a recorded application version alone does not identify the remote engine revision. Both should be recorded when reporting a run.
39
+
40
+ ### CUDA runner
41
+
42
  The runner loads `Qwen/Qwen3.5-0.8B` at revision `2fc06364715b967f1860aea9cf38778875588b17`. The implementation uses `Qwen3_5ForConditionalGeneration`, its text decoder layers, float32 computation, eager attention, and the first process-visible CUDA device. It checks for 24 decoder layers; the geometry and calibration code assume hidden width 1,024. The backbone is in evaluation mode, its parameters have gradients disabled, and calibration and generation run without gradient tracking.
43
 
44
  ![Connection workspace with SSH settings and the Slurm GPU resource request. The client is offline in this capture.](paper/figures/screenshot-01.png)
 
258
 
259
  JSON writes use temporary-file replacement. The companion text file is written normally and may be incomplete if interrupted during that write. Reports are incremental records, not automatic resume checkpoints: rerunning starts over and overwrites the selected output paths. Use a distinct output filename for each experiment. Reports contain the input text and should be treated as document-bearing artifacts.
260
 
261
+ The desktop document view is a presentation layer over these artifacts. The published client displays generated passages separately from source text and diagnostics; its text exports can therefore differ from the runner's assembled file, which includes retained originals. The downloadable report is needed to distinguish generated, retained, failed, and unprocessed passages. Reconnecting can recover an existing job and its outputs, but this client recovery does not make the runner's incremental report a resumable generation checkpoint.
262
+
263
  ## Engineering checks and evidence
264
 
265
  Smoke mode is the default and operates on one supplied passage. It runs baseline, zero-strength, positive-valence, negative-valence, and restored-baseline conditions. Positive and negative conditions use coefficient vectors $(0.8,0,0)$ and $(-0.8,0,0)$. The third coordinate zero corresponds to intensity 0.5.
 
270
 
271
  For the November 13 revision, seven CPU policy tests passed, Python and shell syntax were checked, and CLI loading was verified. Tests cover such behavior as unchanged requested controls, paragraph allowance accounting, draft retention, sentence cleanup, and continuing after a failed chunk. They do not execute the CUDA model. The current revision has not yet been run on an ARC GPU. A successful GPU run was reported for an earlier revision on November 12; it is historical evidence, not validation of the current code.
272
 
273
+ The desktop release also has its own validation record. Its published version 1.0.4 documentation reports native Swift tests, 14 remote-agent tests, a completed sample rewrite, and an earlier GPU setup on an NVIDIA A100-SXM4-80GB. These are release-specific engineering observations, not measurements of emotional accuracy or validation of later changes to the remote runner. The screenshots show the native application's workspaces, including offline states where indicated.
274
+
275
  ## Reproduction
276
 
277
+ For the desktop workflow, download the native macOS application from the repository's macos directory on Hugging Face, unpack it, and open AFFECTOR ARC.app. Configure the connection profile for the user's own ARC login, SSH authentication, and Slurm allocation. After connecting, install or update the remote source and prepare the GPU environment as needed. Import a document and geometry, adjust the settings, and choose Transform on ARC. Monitor the submitted job in Jobs + results and download its input, output, report, geometry, and logs. The published desktop README identifies the application as version 1.0.4 and describes its build as ad-hoc signed.
278
+
279
+ The following commands provide the separate command-line workflow. They run inside a suitable ARC GPU allocation from a fresh repository copy:
280
 
281
  ```bash
282
  bash setup.sh
 
314
 
315
  ## Implementation sources
316
 
317
+ This report covers the native macOS client, its SSH request agent, and the CUDA runner. The desktop release and its source are available alongside the remote engine:
318
 
319
+ - [Native macOS application, Swift source, and release documentation](https://huggingface.co/will-taggart/AFFECTOR-ARC/tree/main/macos)
320
  - [CUDA runner and smoke protocol](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py)
321
  - [Document transformation and incremental output](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/document_run.py)
322
  - [Calibration, displacement math, hooks, and decoding](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/engine/steering.py)
paper/AFFECTOR-ARC-ACM-source.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b7ff9d46195beb92ff6088f52b71154a22bb6d94baf70e1555f710ac70a0407
3
- size 5205410
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:761494d17669ce0ca24001000bfa75f1376c1a3a8007c8ef87c6d1df1ad9f0e9
3
+ size 5213478
paper/AFFECTOR-ARC-ACM.pdf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:896af1e0e290fa6f5af60068713212c70cae9a339335322e82f090cf8392ef4d
3
- size 2476822
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf072babff6b3f33eb7160e0c03b6b7bc4316ec8844aa0230785c0f9e8f4343
3
+ size 2481206
paper/AFFECTOR-ARC-ACM.tex CHANGED
@@ -35,34 +35,19 @@ Activation Steering}
35
  \affiliation{\department{Modern and Classical Languages and Literatures}
36
  \institution{Virginia Tech}\city{Blacksburg}\state{Virginia}\country{USA}}
37
  \email{wtaggart@vt.edu}
38
- \subtitle{Technical Report: November 13, 2026}
39
  \begin{abstract}
40
- AFFECTOR-ARC is an experimental command-line system for rewriting text
41
- under a user-defined emotional trajectory. It runs a frozen Qwen3.5-0.8B
42
- model on an NVIDIA GPU and changes selected internal activations during
43
- generation. A trajectory specifies valence, inward/outward emotional
44
- orientation, and intensity across normalized document position. Small
45
- sets of contrasting English passages establish three activation
46
- directions at each selected transformer layer. At inference time, the
47
- requested coordinates determine a weighted displacement, scaled relative
48
- to the current hidden-state magnitude, smoothed across decoding steps,
49
- and constrained by an RMS budget. Paired hooks apply this displacement
50
- to both the feed-forward input and its residual path. Document rewriting
51
- combines these interventions with four editing styles, sentence-aware
52
- segmentation, bounded generation, and incremental reporting. This report
53
- derives the mechanism from its implemented operations and distinguishes
54
- numerical controls from emotional outcomes. CPU policy tests pass; the
55
- current revision still requires CUDA validation. No measured claim of
56
- emotional accuracy, semantic preservation, or multilingual effectiveness
57
- is made.
58
  \end{abstract}
59
  \keywords{activation steering, emotional text generation, transformer models, controllable generation}
60
  \maketitle
61
  \section{Purpose and Research Context}\label{literature-review-activation-steering-and-emotion}\label{problem-and-operating-principle}
62
 
63
- AFFECTOR-ARC investigates how a prescribed emotional progression can influence a document rewrite on an allocated GPU. A user supplies a UTF-8 text and an ordered sequence of valence, inward/outward emotional orientation, and intensity coordinates. The runner maps document positions to that sequence and converts the sampled coordinates into activation displacements during generation. Here, geometry means a path through a three-dimensional coordinate space, with layer settings and optional calibration matrices. It expresses a desired progression rather than a surface reconstructed from text or a constraint applied directly to individual words.
64
 
65
- The intervention acts on the numerical hidden states used to predict successive tokens while the model's stored parameters remain fixed. This approach builds on contrastive activation steering: Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples \cite{turner2023actadd,panickssery2024caa}. AFFECTOR-ARC uses small sets of contrasting passages to establish emotional directions at selected layers, then applies coordinate-dependent displacements as each passage is rewritten. The contribution is an inspectable implementation of this mapping and its operational controls, not a claim that the emotional coordinates uniquely determine a continuation.
 
 
66
 
67
  \begin{figure}[!htb]
68
  \centering
@@ -72,16 +57,24 @@ The intervention acts on the numerical hidden states used to predict successive
72
  \label{fig:app-screen-2}
73
  \end{figure}
74
 
75
- Research connecting model emotion spaces with human valence/arousal judgments provides motivation for coordinate-based experimentation. Wu and colleagues report concept-based steering across linguistic-cultural settings \cite{wu2025emotion}, while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality \cite{diallo2026style}. Their findings make human interpretation central to evaluation, but they do not calibrate the present inward/outward axis or RMS-scaled settings. A text's emotional reading, its requested coordinates, and the model's hidden states remain distinct objects linked by an experimental calibration.
76
 
77
- That distinction matters when selecting layers and combining axes. Shu and colleagues find uneven causal organization across emotion categories in sparse-feature interventions for recognition \cite{shu2026emotion}; Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers \cite{wang2026readbest}. Ha and colleagues likewise find that supportive-empathy directions are only partially separable \cite{ha2026empathy}. Automated vector extraction and context-dependent strength offer further approaches to calibration and control \cite{cui2025pas,ferrando2025dsas}. These studies motivate layer sweeps, cross-axis tests, and adaptive controls, while the present runner uses an explicit coordinate mixture with user-selected settings.
78
 
79
- Generation limits and failure reporting are part of the same research problem. E-STEER reports non-monotonic effects of emotional interventions across several tasks \cite{sun2026emotion}, and Jeong observes both emotional changes and degeneration in small models \cite{jeong2026emotion}. Stronger settings therefore cannot be assumed to improve transfer. The runner offers a rewrite mode that processes a document in chunks and records attempts and failures, and a smoke mode with five controlled generation conditions for checking intervention and cleanup behavior. Its scope is the command-line CUDA computation illustrated alongside the desktop client's workspaces; the runner itself supplies neither a hosted service, conversational history, nor automatic emotional scoring.
80
 
81
- This operational scope determines the evidence needed to assess the system. SteerScope evaluates efficacy together with side effects, generalization, and dependence on steering data, and finds no general advantage of activation methods over prompt steering in its tested trade-offs \cite{yang2026steerscope}. AFFECTOR-ARC therefore requires prompt-only and unsteered baselines, blinded emotional and quality ratings, content-change assessment, and complete reporting of repetition and truncation. The report documents the implemented mechanism and engineering checks; these broader comparisons and an empirically established operating range remain future work.
82
 
83
  \section{Runtime and data flow}\label{runtime-and-data-flow}
84
 
 
 
 
 
 
 
 
 
85
 
86
  \begin{figure}[!htb]
87
  \centering
@@ -527,6 +520,8 @@ distinct output filename for each experiment. Reports contain the input
527
  text and should be treated as document-bearing artifacts.
528
 
529
 
 
 
530
  \section{Engineering checks and
531
  evidence}\label{engineering-checks-and-evidence}
532
 
@@ -564,9 +559,13 @@ has not yet been run on an ARC GPU. A successful GPU run was reported
564
  for an earlier revision on November 12; it is historical evidence, not
565
  validation of the current code.
566
 
 
 
567
  \section{Reproduction}\label{reproduction}
568
 
569
- Inside a suitable ARC GPU allocation, from a fresh repository copy:
 
 
570
 
571
  \begin{verbatim}
572
  bash setup.sh
@@ -641,11 +640,12 @@ prompt wording alone does not establish it.
641
 
642
  \section{Implementation sources}\label{implementation-sources}
643
 
644
- This report describes the repository's executable operations rather than
645
- relying on another application's interface or documentation.
646
 
647
  \begin{itemize}
648
  \tightlist
 
 
649
  \item
650
  \href{https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py}{CUDA
651
  runner and smoke protocol}
@@ -692,7 +692,7 @@ and limitations are stated separately in this report.
692
  \section*{Suggested citation}
693
  William Taggart. 2026. AFFECTOR-ARC: Emotional Trajectory Control
694
  through Transformer Activation Steering. Technical report. Modern and
695
- Classical Languages and Literatures, Virginia Tech. November 13, 2026.
696
  \url{https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/TECHNICAL_REPORT.md}
697
 
698
  \end{document}
 
35
  \affiliation{\department{Modern and Classical Languages and Literatures}
36
  \institution{Virginia Tech}\city{Blacksburg}\state{Virginia}\country{USA}}
37
  \email{wtaggart@vt.edu}
38
+ \subtitle{Technical Report: November 14, 2026}
39
  \begin{abstract}
40
+ AFFECTOR-ARC is an experimental text-rewriting system with a native macOS application and a command-line CUDA runner. The desktop application manages documents, emotional geometries, SSH connections, Slurm GPU jobs, and downloaded results; the runner executes a frozen Qwen3.5-0.8B model on an allocated ARC GPU. A trajectory specifies valence, inward/outward emotional orientation, and intensity across normalized document position. Contrasting English passages establish three activation directions at each selected transformer layer. During generation, trajectory coordinates determine a displacement scaled to the hidden-state magnitude, smoothed across decoding steps, and constrained by an RMS budget. Paired hooks apply it to the feed-forward input and residual path. Four editing styles, sentence-aware segmentation, bounded generation, and incremental reports make the intervention available within a document workflow. This report describes both interfaces and derives the steering mechanism, while distinguishing implementation checks from evidence of emotional effectiveness. Earlier desktop GPU runs and CPU policy tests are documented separately; they do not validate every subsequent runner revision or establish emotional accuracy, semantic preservation, or multilingual effectiveness.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  \end{abstract}
42
  \keywords{activation steering, emotional text generation, transformer models, controllable generation}
43
  \maketitle
44
  \section{Purpose and Research Context}\label{literature-review-activation-steering-and-emotion}\label{problem-and-operating-principle}
45
 
46
+ AFFECTOR-ARC investigates whether a writer can guide the emotional progression of a document by specifying a trajectory and intervening in a language model's internal computation. The practical aim is to make that experiment usable across a complete rewrite: the writer selects a text, supplies an emotional geometry, adjusts the intervention, and inspects the resulting passages and diagnostics. A native macOS application brings these activities into a workspace, while SSH and Slurm connect that workspace to a GPU allocation on Virginia Tech ARC. A command-line runner exposes the computation separately for scripted experiments and reproducible execution.
47
 
48
+ The geometry gives this workflow a common representation. It is an ordered path through valence, inward/outward emotional orientation, and intensity, accompanied by layer settings and optional calibration matrices. Sampling the path at successive document positions supplies the coordinates used during rewriting. Those coordinates become displacements of the model's hidden states, so the desired progression acts on the computation that produces tokens rather than prescribing particular words. The model's stored parameters remain fixed throughout.
49
+
50
+ This mechanism builds on contrastive activation steering. Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples \cite{turner2023actadd,panickssery2024caa}. AFFECTOR-ARC applies the same broad principle to small sets of emotionally contrasting passages, then mixes the resulting directions according to the requested trajectory. The central research question is how reliably this mapping can influence a sustained rewrite, given that a numerical displacement need not produce a unique or consistent emotional interpretation.
51
 
52
  \begin{figure}[!htb]
53
  \centering
 
57
  \label{fig:app-screen-2}
58
  \end{figure}
59
 
60
+ That question connects the implementation to research on the relation between model representations and human judgments. Wu and colleagues study concept-based emotional steering across linguistic-cultural settings, while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality \cite{wu2025emotion,diallo2026style}. These studies motivate coordinate-based experiments whose outcomes are judged through readers' interpretations. They do not, however, establish the validity of this system's inward/outward axis or calibrate its RMS-scaled controls. The requested trajectory, the activation displacement, and the emotion perceived in the output must therefore be evaluated as related but distinct quantities.
61
 
62
+ The reliability of that relationship also depends on where and how the intervention is applied. Shu and colleagues find uneven causal organization across emotion categories, and Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers \cite{shu2026emotion,wang2026readbest}. Ha and colleagues' finding that supportive-empathy directions are only partially separable further cautions against treating emotional axes as independent controls \cite{ha2026empathy}. Automated vector extraction and context-dependent strength offer approaches to these calibration problems \cite{cui2025pas,ferrando2025dsas}. AFFECTOR-ARC makes layer weights and axis mixtures explicit so that such questions can be investigated, although its current runner uses user-selected settings rather than an adaptive emotional-feedback controller.
63
 
64
+ Applying those settings across a document makes generation stability part of the same problem. E-STEER reports non-monotonic effects of emotional interventions, and Jeong observes both emotional changes and degeneration in small models \cite{sun2026emotion,jeong2026emotion}. A stronger displacement can thus disrupt a rewrite without bringing it closer to the intended trajectory. The system addresses the operational consequences through bounded generation, repetition checks, passage-level failure records, and a desktop workflow for reviewing jobs and results. These safeguards preserve an inspectable experiment; they do not establish that a completed rewrite meets its emotional target.
65
 
66
+ Evaluation must consequently consider emotional alignment together with fluency, content change, and failure rates. SteerScope examines efficacy, side effects, generalization, and dependence on steering data, finding no general advantage over prompt steering in its tested trade-offs \cite{yang2026steerscope}. For AFFECTOR-ARC, this motivates comparisons with prompt-only and unsteered rewriting, blinded emotional and quality ratings, and complete reporting of retained originals, repetition, and truncation. The scope of this report is the desktop-to-cluster workflow and the implemented steering procedure, including their engineering checks. Establishing emotional effectiveness and a reliable operating range remains an empirical task.
67
 
68
  \section{Runtime and data flow}\label{runtime-and-data-flow}
69
 
70
+ \subsection{Native macOS client and remote execution}
71
+
72
+ The native SwiftUI application is distributed on Hugging Face for Apple Silicon Macs running macOS 15 or later. Its connection workspace configures SSH access and the Slurm resource request. The document workspace holds the input and generated text; the shape and weights workspace supports importing, converting, and editing geometries and intervention settings. Jobs and results controls expose remote progress, diagnostics, and output downloads. The application also manages Hugging Face source updates and submits GPU-environment setup through Slurm.
73
+
74
+ The Mac serves as the client: lightweight SSH requests manage files and jobs, while model setup and execution run in requested GPU allocations. The bundled Python remote agent handles requests over SSH without a persistent listening server. The desktop interface and the command-line runner are separately versioned components, so a recorded application version alone does not identify the remote engine revision. Both should be recorded when reporting a run.
75
+
76
+ \subsection{CUDA runner}
77
+
78
 
79
  \begin{figure}[!htb]
80
  \centering
 
520
  text and should be treated as document-bearing artifacts.
521
 
522
 
523
+ The desktop document view is a presentation layer over these artifacts. The published client displays generated passages separately from source text and diagnostics; its text exports can therefore differ from the runner's assembled file, which includes retained originals. The downloadable report is needed to distinguish generated, retained, failed, and unprocessed passages. Reconnecting can recover an existing job and its outputs, but this client recovery does not make the runner's incremental report a resumable generation checkpoint.
524
+
525
  \section{Engineering checks and
526
  evidence}\label{engineering-checks-and-evidence}
527
 
 
559
  for an earlier revision on November 12; it is historical evidence, not
560
  validation of the current code.
561
 
562
+ The desktop release also has its own validation record. Its published version 1.0.4 documentation reports native Swift tests, 14 remote-agent tests, a completed sample rewrite, and an earlier GPU setup on an NVIDIA A100-SXM4-80GB. These are release-specific engineering observations, not measurements of emotional accuracy or validation of later changes to the remote runner. The screenshots show the native application's workspaces, including offline states where indicated.
563
+
564
  \section{Reproduction}\label{reproduction}
565
 
566
+ For the desktop workflow, download the native macOS application from the repository's macos directory on Hugging Face, unpack it, and open AFFECTOR ARC.app. Configure the connection profile for the user's own ARC login, SSH authentication, and Slurm allocation. After connecting, install or update the remote source and prepare the GPU environment as needed. Import a document and geometry, adjust the settings, and choose Transform on ARC. Monitor the submitted job in Jobs + results and download its input, output, report, geometry, and logs. The published desktop README identifies the application as version 1.0.4 and describes its build as ad-hoc signed.
567
+
568
+ The following commands provide the separate command-line workflow. They run inside a suitable ARC GPU allocation from a fresh repository copy:
569
 
570
  \begin{verbatim}
571
  bash setup.sh
 
640
 
641
  \section{Implementation sources}\label{implementation-sources}
642
 
643
+ This report covers the native macOS client, its SSH request agent, and the CUDA runner. The desktop release and its source are available alongside the remote engine:
 
644
 
645
  \begin{itemize}
646
  \tightlist
647
+ \item
648
+ \href{https://huggingface.co/will-taggart/AFFECTOR-ARC/tree/main/macos}{Native macOS application, Swift source, and release documentation}
649
  \item
650
  \href{https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py}{CUDA
651
  runner and smoke protocol}
 
692
  \section*{Suggested citation}
693
  William Taggart. 2026. AFFECTOR-ARC: Emotional Trajectory Control
694
  through Transformer Activation Steering. Technical report. Modern and
695
+ Classical Languages and Literatures, Virginia Tech. November 14, 2026.
696
  \url{https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/TECHNICAL_REPORT.md}
697
 
698
  \end{document}
paper/PAPER-SHA256SUMS.txt CHANGED
@@ -1,11 +1,11 @@
1
- 0b7ff9d46195beb92ff6088f52b71154a22bb6d94baf70e1555f710ac70a0407 AFFECTOR-ARC-ACM-source.zip
2
  d78577482f74cba4163db18d88af82786c923d72cd09607bde62cb747c645c5d AFFECTOR-ARC-ACM.bbl
3
- 896af1e0e290fa6f5af60068713212c70cae9a339335322e82f090cf8392ef4d AFFECTOR-ARC-ACM.pdf
4
- 9ef3bfea1bd825772d3cf6a92c39f23921ed3a5340e41fc5d6c723b213377c3f AFFECTOR-ARC-ACM.tex
5
  00fe34363158541d8d41414f548a2a6a7fd73b147e025b8bc2ef042f9dba6d85 ILLUSTRATIONS.json
6
  d14edda139a36c0bac8b56d02e5cda63ab7558c6db1424f1087189a9429bfaf0 LITERATURE_SOURCES.md
7
  b9375d5aa1da63a0a2773da47c8dce77eaad36a34265f9b36a569671e275ad9b README.md
8
- 3ea499fef150bf7afd74cfc8a736271f3164100d7ada90f7aff6552d9de4ff0f TECHNICAL_PAPER.md
9
  b1af14ec24b576fa1675395d73e75adfa4f5174d52902866ffef71374ddbc852 figure-specifications.json
10
  b072894d9761bb46543f0c584cf781aaedce49100a489a2bc1e2b48b9ad47e10 figures/illustration-01.pdf
11
  68020194c3306e7fecf75e94343ea2a3cb0af6d186c2d8d93220cbc6dec12e6f figures/illustration-01.png
@@ -19,4 +19,4 @@ bb8302843abc13419014ea6a06d63edfe6de9e02df248ee4c1ae8e3b0e6fc0a8 figures/illust
19
  5f4e1daaf625926a768773cfcb80287cb6c25ad793c4510fbecc6aaa57f4b04a figures/illustration-05.png
20
  9257f38423bd7e496f1a0916c0fbaefbfb32ab544a684ca9a411508201f0535e references.bib
21
  eed8b979a5a299b42e925d9027332e7df876400dcef046f2cfe26beef91d1189 render_figures.py
22
- 3ea499fef150bf7afd74cfc8a736271f3164100d7ada90f7aff6552d9de4ff0f source.md
 
1
+ 761494d17669ce0ca24001000bfa75f1376c1a3a8007c8ef87c6d1df1ad9f0e9 AFFECTOR-ARC-ACM-source.zip
2
  d78577482f74cba4163db18d88af82786c923d72cd09607bde62cb747c645c5d AFFECTOR-ARC-ACM.bbl
3
+ faf072babff6b3f33eb7160e0c03b6b7bc4316ec8844aa0230785c0f9e8f4343 AFFECTOR-ARC-ACM.pdf
4
+ b39b322e1e0ef985284751bc7be4cd9da3994c575b1986b4cd1f5c5f6c64af49 AFFECTOR-ARC-ACM.tex
5
  00fe34363158541d8d41414f548a2a6a7fd73b147e025b8bc2ef042f9dba6d85 ILLUSTRATIONS.json
6
  d14edda139a36c0bac8b56d02e5cda63ab7558c6db1424f1087189a9429bfaf0 LITERATURE_SOURCES.md
7
  b9375d5aa1da63a0a2773da47c8dce77eaad36a34265f9b36a569671e275ad9b README.md
8
+ 2ebd4f309183a1f91c471c92c92addb179c8c550ea465daddfc9c5502a0d1527 TECHNICAL_PAPER.md
9
  b1af14ec24b576fa1675395d73e75adfa4f5174d52902866ffef71374ddbc852 figure-specifications.json
10
  b072894d9761bb46543f0c584cf781aaedce49100a489a2bc1e2b48b9ad47e10 figures/illustration-01.pdf
11
  68020194c3306e7fecf75e94343ea2a3cb0af6d186c2d8d93220cbc6dec12e6f figures/illustration-01.png
 
19
  5f4e1daaf625926a768773cfcb80287cb6c25ad793c4510fbecc6aaa57f4b04a figures/illustration-05.png
20
  9257f38423bd7e496f1a0916c0fbaefbfb32ab544a684ca9a411508201f0535e references.bib
21
  eed8b979a5a299b42e925d9027332e7df876400dcef046f2cfe26beef91d1189 render_figures.py
22
+ 2ebd4f309183a1f91c471c92c92addb179c8c550ea465daddfc9c5502a0d1527 source.md
paper/TECHNICAL_PAPER.md CHANGED
@@ -3,32 +3,42 @@
3
  **William Taggart**
4
  Modern and Classical Languages and Literatures, Virginia Tech
5
  Email: wtaggart@vt.edu
6
- **Technical report · November 13, 2026 · Revision 0.2**
7
 
8
  ## Abstract
9
 
10
- AFFECTOR-ARC is an experimental command-line system for rewriting text under a user-defined emotional trajectory. It runs a frozen Qwen3.5-0.8B model on an NVIDIA GPU and changes selected internal activations during generation. A trajectory specifies valence, inward/outward emotional orientation, and intensity across normalized document position. Small sets of contrasting English passages establish three activation directions at each selected transformer layer. At inference time, the requested coordinates determine a weighted displacement, scaled relative to the current hidden-state magnitude, smoothed across decoding steps, and constrained by an RMS budget. Paired hooks apply this displacement to both the feed-forward input and its residual path. Document rewriting combines these interventions with four editing styles, sentence-aware segmentation, bounded generation, and incremental reporting. This report derives the mechanism from its implemented operations and distinguishes numerical controls from emotional outcomes. CPU policy tests pass; the current revision still requires CUDA validation. No measured claim of emotional accuracy, semantic preservation, or multilingual effectiveness is made.
11
 
12
  ## Purpose and Research Context
13
 
14
- AFFECTOR-ARC investigates how a prescribed emotional progression can influence a document rewrite on an allocated GPU. A user supplies a UTF-8 text and an ordered sequence of valence, inward/outward emotional orientation, and intensity coordinates. The runner maps document positions to that sequence and converts the sampled coordinates into activation displacements during generation. Here, geometry means a path through a three-dimensional coordinate space, with layer settings and optional calibration matrices. It expresses a desired progression rather than a surface reconstructed from text or a constraint applied directly to individual words.
15
 
16
- The intervention acts on the numerical hidden states used to predict successive tokens while the model's stored parameters remain fixed. This approach builds on contrastive activation steering: Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples ([Turner et al., 2023](https://arxiv.org/abs/2308.10248v1); [Panickssery et al., 2024](https://arxiv.org/abs/2312.06681v4)). AFFECTOR-ARC uses small sets of contrasting passages to establish emotional directions at selected layers, then applies coordinate-dependent displacements as each passage is rewritten. The contribution is an inspectable implementation of this mapping and its operational controls, not a claim that the emotional coordinates uniquely determine a continuation.
 
 
17
 
18
  ![Document workspace displaying an existing Little Red Riding Hood input and rewrite.](figures/screenshot-02.png)
19
 
20
  *Document workspace displaying an existing Little Red Riding Hood input and rewrite.*
21
 
22
- Research connecting model emotion spaces with human valence/arousal judgments provides motivation for coordinate-based experimentation. Wu and colleagues report concept-based steering across linguistic-cultural settings ([Wu et al., 2025](https://arxiv.org/abs/2506.13978v1)), while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality ([Diallo et al., 2026](https://arxiv.org/abs/2601.21505v1)). Their findings make human interpretation central to evaluation, but they do not calibrate the present inward/outward axis or RMS-scaled settings. A text's emotional reading, its requested coordinates, and the model's hidden states remain distinct objects linked by an experimental calibration.
23
 
24
- That distinction matters when selecting layers and combining axes. Shu and colleagues find uneven causal organization across emotion categories in sparse-feature interventions for recognition ([Shu et al., 2026](https://arxiv.org/abs/2604.25866v3)); Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers ([Wang et al., 2026](https://arxiv.org/abs/2609.22135v1)). Ha and colleagues likewise find that supportive-empathy directions are only partially separable ([Ha et al., 2026](https://arxiv.org/abs/2609.15654v1)). Automated vector extraction and context-dependent strength offer further approaches to calibration and control ([Cui et al., 2025](https://arxiv.org/abs/2509.22739v3); [Ferrando et al., 2025](https://arxiv.org/abs/2512.03661v2)). These studies motivate layer sweeps, cross-axis tests, and adaptive controls, while the present runner uses an explicit coordinate mixture with user-selected settings.
25
 
26
- Generation limits and failure reporting are part of the same research problem. E-STEER reports non-monotonic effects of emotional interventions across several tasks ([Sun et al., 2026](https://arxiv.org/abs/2604.00005v1)), and Jeong observes both emotional changes and degeneration in small models ([Jeong, 2026](https://arxiv.org/abs/2604.04064v1)). Stronger settings therefore cannot be assumed to improve transfer. The runner offers a rewrite mode that processes a document in chunks and records attempts and failures, and a smoke mode with five controlled generation conditions for checking intervention and cleanup behavior. Its scope is the command-line CUDA computation illustrated alongside the desktop client's workspaces; the runner itself supplies neither a hosted service, conversational history, nor automatic emotional scoring.
27
 
28
- This operational scope determines the evidence needed to assess the system. SteerScope evaluates efficacy together with side effects, generalization, and dependence on steering data, and finds no general advantage of activation methods over prompt steering in its tested trade-offs ([Yang et al., 2026](https://arxiv.org/abs/2610.07722v1)). AFFECTOR-ARC therefore requires prompt-only and unsteered baselines, blinded emotional and quality ratings, content-change assessment, and complete reporting of repetition and truncation. The report documents the implemented mechanism and engineering checks; these broader comparisons and an empirically established operating range remain future work.
29
 
30
  ## Runtime and data flow
31
 
 
 
 
 
 
 
 
 
32
  The runner loads `Qwen/Qwen3.5-0.8B` at revision `2fc06364715b967f1860aea9cf38778875588b17`. The implementation uses `Qwen3_5ForConditionalGeneration`, its text decoder layers, float32 computation, eager attention, and the first process-visible CUDA device. It checks for 24 decoder layers; the geometry and calibration code assume hidden width 1,024. The backbone is in evaluation mode, its parameters have gradients disabled, and calibration and generation run without gradient tracking.
33
 
34
  ![Connection workspace with SSH settings and the Slurm GPU resource request. The client is offline in this capture.](figures/screenshot-01.png)
@@ -248,6 +258,8 @@ Successful generation records include stopping reason, token count, elapsed time
248
 
249
  JSON writes use temporary-file replacement. The companion text file is written normally and may be incomplete if interrupted during that write. Reports are incremental records, not automatic resume checkpoints: rerunning starts over and overwrites the selected output paths. Use a distinct output filename for each experiment. Reports contain the input text and should be treated as document-bearing artifacts.
250
 
 
 
251
  ## Engineering checks and evidence
252
 
253
  Smoke mode is the default and operates on one supplied passage. It runs baseline, zero-strength, positive-valence, negative-valence, and restored-baseline conditions. Positive and negative conditions use coefficient vectors $(0.8,0,0)$ and $(-0.8,0,0)$. The third coordinate zero corresponds to intensity 0.5.
@@ -258,9 +270,13 @@ Smoke mode defaults to the original 128-token allowance and 600-second time thre
258
 
259
  For the November 13 revision, seven CPU policy tests passed, Python and shell syntax were checked, and CLI loading was verified. Tests cover such behavior as unchanged requested controls, paragraph allowance accounting, draft retention, sentence cleanup, and continuing after a failed chunk. They do not execute the CUDA model. The current revision has not yet been run on an ARC GPU. A successful GPU run was reported for an earlier revision on November 12; it is historical evidence, not validation of the current code.
260
 
 
 
261
  ## Reproduction
262
 
263
- Inside a suitable ARC GPU allocation, from a fresh repository copy:
 
 
264
 
265
  ```bash
266
  bash setup.sh
@@ -298,8 +314,9 @@ Changing to a larger model requires new architecture validation, basis calibrati
298
 
299
  ## Implementation sources
300
 
301
- This report describes the repository's executable operations rather than relying on another application's interface or documentation.
302
 
 
303
  - [CUDA runner and smoke protocol](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py)
304
  - [Document transformation and incremental output](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/document_run.py)
305
  - [Calibration, displacement math, hooks, and decoding](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/engine/steering.py)
 
3
  **William Taggart**
4
  Modern and Classical Languages and Literatures, Virginia Tech
5
  Email: wtaggart@vt.edu
6
+ **Technical report · November 14, 2026 · Revision 0.3**
7
 
8
  ## Abstract
9
 
10
+ AFFECTOR-ARC is an experimental text-rewriting system with a native macOS application and a command-line CUDA runner. The desktop application manages documents, emotional geometries, SSH connections, Slurm GPU jobs, and downloaded results; the runner executes a frozen Qwen3.5-0.8B model on an allocated ARC GPU. A trajectory specifies valence, inward/outward emotional orientation, and intensity across normalized document position. Contrasting English passages establish three activation directions at each selected transformer layer. During generation, trajectory coordinates determine a displacement scaled to the hidden-state magnitude, smoothed across decoding steps, and constrained by an RMS budget. Paired hooks apply it to the feed-forward input and residual path. Four editing styles, sentence-aware segmentation, bounded generation, and incremental reports make the intervention available within a document workflow. This report describes both interfaces and derives the steering mechanism, while distinguishing implementation checks from evidence of emotional effectiveness. Earlier desktop GPU runs and CPU policy tests are documented separately; they do not validate every subsequent runner revision or establish emotional accuracy, semantic preservation, or multilingual effectiveness.
11
 
12
  ## Purpose and Research Context
13
 
14
+ AFFECTOR-ARC investigates whether a writer can guide the emotional progression of a document by specifying a trajectory and intervening in a language model's internal computation. The practical aim is to make that experiment usable across a complete rewrite: the writer selects a text, supplies an emotional geometry, adjusts the intervention, and inspects the resulting passages and diagnostics. A native macOS application brings these activities into a workspace, while SSH and Slurm connect that workspace to a GPU allocation on Virginia Tech ARC. A command-line runner exposes the computation separately for scripted experiments and reproducible execution.
15
 
16
+ The geometry gives this workflow a common representation. It is an ordered path through valence, inward/outward emotional orientation, and intensity, accompanied by layer settings and optional calibration matrices. Sampling the path at successive document positions supplies the coordinates used during rewriting. Those coordinates become displacements of the model's hidden states, so the desired progression acts on the computation that produces tokens rather than prescribing particular words. The model's stored parameters remain fixed throughout.
17
+
18
+ This mechanism builds on contrastive activation steering. Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples ([Turner et al., 2023](https://arxiv.org/abs/2308.10248v1); [Panickssery et al., 2024](https://arxiv.org/abs/2312.06681v4)). AFFECTOR-ARC applies the same broad principle to small sets of emotionally contrasting passages, then mixes the resulting directions according to the requested trajectory. The central research question is how reliably this mapping can influence a sustained rewrite, given that a numerical displacement need not produce a unique or consistent emotional interpretation.
19
 
20
  ![Document workspace displaying an existing Little Red Riding Hood input and rewrite.](figures/screenshot-02.png)
21
 
22
  *Document workspace displaying an existing Little Red Riding Hood input and rewrite.*
23
 
24
+ That question connects the implementation to research on the relation between model representations and human judgments. Wu and colleagues study concept-based emotional steering across linguistic-cultural settings, while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality ([Wu et al., 2025](https://arxiv.org/abs/2506.13978v1); [Diallo et al., 2026](https://arxiv.org/abs/2601.21505v1)). These studies motivate coordinate-based experiments whose outcomes are judged through readers' interpretations. They do not, however, establish the validity of this system's inward/outward axis or calibrate its RMS-scaled controls. The requested trajectory, the activation displacement, and the emotion perceived in the output must therefore be evaluated as related but distinct quantities.
25
 
26
+ The reliability of that relationship also depends on where and how the intervention is applied. Shu and colleagues find uneven causal organization across emotion categories, and Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers ([Shu et al., 2026](https://arxiv.org/abs/2604.25866v3); [Wang et al., 2026](https://arxiv.org/abs/2609.22135v1)). Ha and colleagues' finding that supportive-empathy directions are only partially separable further cautions against treating emotional axes as independent controls ([Ha et al., 2026](https://arxiv.org/abs/2609.15654v1)). Automated vector extraction and context-dependent strength offer approaches to these calibration problems ([Cui et al., 2025](https://arxiv.org/abs/2509.22739v3); [Ferrando et al., 2025](https://arxiv.org/abs/2512.03661v2)). AFFECTOR-ARC makes layer weights and axis mixtures explicit so that such questions can be investigated, although its current runner uses user-selected settings rather than an adaptive emotional-feedback controller.
27
 
28
+ Applying those settings across a document makes generation stability part of the same problem. E-STEER reports non-monotonic effects of emotional interventions, and Jeong observes both emotional changes and degeneration in small models ([Sun et al., 2026](https://arxiv.org/abs/2604.00005v1); [Jeong, 2026](https://arxiv.org/abs/2604.04064v1)). A stronger displacement can thus disrupt a rewrite without bringing it closer to the intended trajectory. The system addresses the operational consequences through bounded generation, repetition checks, passage-level failure records, and a desktop workflow for reviewing jobs and results. These safeguards preserve an inspectable experiment; they do not establish that a completed rewrite meets its emotional target.
29
 
30
+ Evaluation must consequently consider emotional alignment together with fluency, content change, and failure rates. SteerScope examines efficacy, side effects, generalization, and dependence on steering data, finding no general advantage over prompt steering in its tested trade-offs ([Yang et al., 2026](https://arxiv.org/abs/2610.07722v1)). For AFFECTOR-ARC, this motivates comparisons with prompt-only and unsteered rewriting, blinded emotional and quality ratings, and complete reporting of retained originals, repetition, and truncation. The scope of this report is the desktop-to-cluster workflow and the implemented steering procedure, including their engineering checks. Establishing emotional effectiveness and a reliable operating range remains an empirical task.
31
 
32
  ## Runtime and data flow
33
 
34
+ ### Native macOS client and remote execution
35
+
36
+ The native SwiftUI application is distributed on Hugging Face for Apple Silicon Macs running macOS 15 or later. Its connection workspace configures SSH access and the Slurm resource request. The document workspace holds the input and generated text; the shape and weights workspace supports importing, converting, and editing geometries and intervention settings. Jobs and results controls expose remote progress, diagnostics, and output downloads. The application also manages Hugging Face source updates and submits GPU-environment setup through Slurm.
37
+
38
+ The Mac serves as the client: lightweight SSH requests manage files and jobs, while model setup and execution run in requested GPU allocations. The bundled Python remote agent handles requests over SSH without a persistent listening server. The desktop interface and the command-line runner are separately versioned components, so a recorded application version alone does not identify the remote engine revision. Both should be recorded when reporting a run.
39
+
40
+ ### CUDA runner
41
+
42
  The runner loads `Qwen/Qwen3.5-0.8B` at revision `2fc06364715b967f1860aea9cf38778875588b17`. The implementation uses `Qwen3_5ForConditionalGeneration`, its text decoder layers, float32 computation, eager attention, and the first process-visible CUDA device. It checks for 24 decoder layers; the geometry and calibration code assume hidden width 1,024. The backbone is in evaluation mode, its parameters have gradients disabled, and calibration and generation run without gradient tracking.
43
 
44
  ![Connection workspace with SSH settings and the Slurm GPU resource request. The client is offline in this capture.](figures/screenshot-01.png)
 
258
 
259
  JSON writes use temporary-file replacement. The companion text file is written normally and may be incomplete if interrupted during that write. Reports are incremental records, not automatic resume checkpoints: rerunning starts over and overwrites the selected output paths. Use a distinct output filename for each experiment. Reports contain the input text and should be treated as document-bearing artifacts.
260
 
261
+ The desktop document view is a presentation layer over these artifacts. The published client displays generated passages separately from source text and diagnostics; its text exports can therefore differ from the runner's assembled file, which includes retained originals. The downloadable report is needed to distinguish generated, retained, failed, and unprocessed passages. Reconnecting can recover an existing job and its outputs, but this client recovery does not make the runner's incremental report a resumable generation checkpoint.
262
+
263
  ## Engineering checks and evidence
264
 
265
  Smoke mode is the default and operates on one supplied passage. It runs baseline, zero-strength, positive-valence, negative-valence, and restored-baseline conditions. Positive and negative conditions use coefficient vectors $(0.8,0,0)$ and $(-0.8,0,0)$. The third coordinate zero corresponds to intensity 0.5.
 
270
 
271
  For the November 13 revision, seven CPU policy tests passed, Python and shell syntax were checked, and CLI loading was verified. Tests cover such behavior as unchanged requested controls, paragraph allowance accounting, draft retention, sentence cleanup, and continuing after a failed chunk. They do not execute the CUDA model. The current revision has not yet been run on an ARC GPU. A successful GPU run was reported for an earlier revision on November 12; it is historical evidence, not validation of the current code.
272
 
273
+ The desktop release also has its own validation record. Its published version 1.0.4 documentation reports native Swift tests, 14 remote-agent tests, a completed sample rewrite, and an earlier GPU setup on an NVIDIA A100-SXM4-80GB. These are release-specific engineering observations, not measurements of emotional accuracy or validation of later changes to the remote runner. The screenshots show the native application's workspaces, including offline states where indicated.
274
+
275
  ## Reproduction
276
 
277
+ For the desktop workflow, download the native macOS application from the repository's macos directory on Hugging Face, unpack it, and open AFFECTOR ARC.app. Configure the connection profile for the user's own ARC login, SSH authentication, and Slurm allocation. After connecting, install or update the remote source and prepare the GPU environment as needed. Import a document and geometry, adjust the settings, and choose Transform on ARC. Monitor the submitted job in Jobs + results and download its input, output, report, geometry, and logs. The published desktop README identifies the application as version 1.0.4 and describes its build as ad-hoc signed.
278
+
279
+ The following commands provide the separate command-line workflow. They run inside a suitable ARC GPU allocation from a fresh repository copy:
280
 
281
  ```bash
282
  bash setup.sh
 
314
 
315
  ## Implementation sources
316
 
317
+ This report covers the native macOS client, its SSH request agent, and the CUDA runner. The desktop release and its source are available alongside the remote engine:
318
 
319
+ - [Native macOS application, Swift source, and release documentation](https://huggingface.co/will-taggart/AFFECTOR-ARC/tree/main/macos)
320
  - [CUDA runner and smoke protocol](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py)
321
  - [Document transformation and incremental output](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/document_run.py)
322
  - [Calibration, displacement math, hooks, and decoding](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/engine/steering.py)
paper/source.md CHANGED
@@ -3,32 +3,42 @@
3
  **William Taggart**
4
  Modern and Classical Languages and Literatures, Virginia Tech
5
  Email: wtaggart@vt.edu
6
- **Technical report · November 13, 2026 · Revision 0.2**
7
 
8
  ## Abstract
9
 
10
- AFFECTOR-ARC is an experimental command-line system for rewriting text under a user-defined emotional trajectory. It runs a frozen Qwen3.5-0.8B model on an NVIDIA GPU and changes selected internal activations during generation. A trajectory specifies valence, inward/outward emotional orientation, and intensity across normalized document position. Small sets of contrasting English passages establish three activation directions at each selected transformer layer. At inference time, the requested coordinates determine a weighted displacement, scaled relative to the current hidden-state magnitude, smoothed across decoding steps, and constrained by an RMS budget. Paired hooks apply this displacement to both the feed-forward input and its residual path. Document rewriting combines these interventions with four editing styles, sentence-aware segmentation, bounded generation, and incremental reporting. This report derives the mechanism from its implemented operations and distinguishes numerical controls from emotional outcomes. CPU policy tests pass; the current revision still requires CUDA validation. No measured claim of emotional accuracy, semantic preservation, or multilingual effectiveness is made.
11
 
12
  ## Purpose and Research Context
13
 
14
- AFFECTOR-ARC investigates how a prescribed emotional progression can influence a document rewrite on an allocated GPU. A user supplies a UTF-8 text and an ordered sequence of valence, inward/outward emotional orientation, and intensity coordinates. The runner maps document positions to that sequence and converts the sampled coordinates into activation displacements during generation. Here, geometry means a path through a three-dimensional coordinate space, with layer settings and optional calibration matrices. It expresses a desired progression rather than a surface reconstructed from text or a constraint applied directly to individual words.
15
 
16
- The intervention acts on the numerical hidden states used to predict successive tokens while the model's stored parameters remain fixed. This approach builds on contrastive activation steering: Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples ([Turner et al., 2023](https://arxiv.org/abs/2308.10248v1); [Panickssery et al., 2024](https://arxiv.org/abs/2312.06681v4)). AFFECTOR-ARC uses small sets of contrasting passages to establish emotional directions at selected layers, then applies coordinate-dependent displacements as each passage is rewritten. The contribution is an inspectable implementation of this mapping and its operational controls, not a claim that the emotional coordinates uniquely determine a continuation.
 
 
17
 
18
  ![Document workspace displaying an existing Little Red Riding Hood input and rewrite.](figures/screenshot-02.png)
19
 
20
  *Document workspace displaying an existing Little Red Riding Hood input and rewrite.*
21
 
22
- Research connecting model emotion spaces with human valence/arousal judgments provides motivation for coordinate-based experimentation. Wu and colleagues report concept-based steering across linguistic-cultural settings ([Wu et al., 2025](https://arxiv.org/abs/2506.13978v1)), while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality ([Diallo et al., 2026](https://arxiv.org/abs/2601.21505v1)). Their findings make human interpretation central to evaluation, but they do not calibrate the present inward/outward axis or RMS-scaled settings. A text's emotional reading, its requested coordinates, and the model's hidden states remain distinct objects linked by an experimental calibration.
23
 
24
- That distinction matters when selecting layers and combining axes. Shu and colleagues find uneven causal organization across emotion categories in sparse-feature interventions for recognition ([Shu et al., 2026](https://arxiv.org/abs/2604.25866v3)); Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers ([Wang et al., 2026](https://arxiv.org/abs/2609.22135v1)). Ha and colleagues likewise find that supportive-empathy directions are only partially separable ([Ha et al., 2026](https://arxiv.org/abs/2609.15654v1)). Automated vector extraction and context-dependent strength offer further approaches to calibration and control ([Cui et al., 2025](https://arxiv.org/abs/2509.22739v3); [Ferrando et al., 2025](https://arxiv.org/abs/2512.03661v2)). These studies motivate layer sweeps, cross-axis tests, and adaptive controls, while the present runner uses an explicit coordinate mixture with user-selected settings.
25
 
26
- Generation limits and failure reporting are part of the same research problem. E-STEER reports non-monotonic effects of emotional interventions across several tasks ([Sun et al., 2026](https://arxiv.org/abs/2604.00005v1)), and Jeong observes both emotional changes and degeneration in small models ([Jeong, 2026](https://arxiv.org/abs/2604.04064v1)). Stronger settings therefore cannot be assumed to improve transfer. The runner offers a rewrite mode that processes a document in chunks and records attempts and failures, and a smoke mode with five controlled generation conditions for checking intervention and cleanup behavior. Its scope is the command-line CUDA computation illustrated alongside the desktop client's workspaces; the runner itself supplies neither a hosted service, conversational history, nor automatic emotional scoring.
27
 
28
- This operational scope determines the evidence needed to assess the system. SteerScope evaluates efficacy together with side effects, generalization, and dependence on steering data, and finds no general advantage of activation methods over prompt steering in its tested trade-offs ([Yang et al., 2026](https://arxiv.org/abs/2610.07722v1)). AFFECTOR-ARC therefore requires prompt-only and unsteered baselines, blinded emotional and quality ratings, content-change assessment, and complete reporting of repetition and truncation. The report documents the implemented mechanism and engineering checks; these broader comparisons and an empirically established operating range remain future work.
29
 
30
  ## Runtime and data flow
31
 
 
 
 
 
 
 
 
 
32
  The runner loads `Qwen/Qwen3.5-0.8B` at revision `2fc06364715b967f1860aea9cf38778875588b17`. The implementation uses `Qwen3_5ForConditionalGeneration`, its text decoder layers, float32 computation, eager attention, and the first process-visible CUDA device. It checks for 24 decoder layers; the geometry and calibration code assume hidden width 1,024. The backbone is in evaluation mode, its parameters have gradients disabled, and calibration and generation run without gradient tracking.
33
 
34
  ![Connection workspace with SSH settings and the Slurm GPU resource request. The client is offline in this capture.](figures/screenshot-01.png)
@@ -248,6 +258,8 @@ Successful generation records include stopping reason, token count, elapsed time
248
 
249
  JSON writes use temporary-file replacement. The companion text file is written normally and may be incomplete if interrupted during that write. Reports are incremental records, not automatic resume checkpoints: rerunning starts over and overwrites the selected output paths. Use a distinct output filename for each experiment. Reports contain the input text and should be treated as document-bearing artifacts.
250
 
 
 
251
  ## Engineering checks and evidence
252
 
253
  Smoke mode is the default and operates on one supplied passage. It runs baseline, zero-strength, positive-valence, negative-valence, and restored-baseline conditions. Positive and negative conditions use coefficient vectors $(0.8,0,0)$ and $(-0.8,0,0)$. The third coordinate zero corresponds to intensity 0.5.
@@ -258,9 +270,13 @@ Smoke mode defaults to the original 128-token allowance and 600-second time thre
258
 
259
  For the November 13 revision, seven CPU policy tests passed, Python and shell syntax were checked, and CLI loading was verified. Tests cover such behavior as unchanged requested controls, paragraph allowance accounting, draft retention, sentence cleanup, and continuing after a failed chunk. They do not execute the CUDA model. The current revision has not yet been run on an ARC GPU. A successful GPU run was reported for an earlier revision on November 12; it is historical evidence, not validation of the current code.
260
 
 
 
261
  ## Reproduction
262
 
263
- Inside a suitable ARC GPU allocation, from a fresh repository copy:
 
 
264
 
265
  ```bash
266
  bash setup.sh
@@ -298,8 +314,9 @@ Changing to a larger model requires new architecture validation, basis calibrati
298
 
299
  ## Implementation sources
300
 
301
- This report describes the repository's executable operations rather than relying on another application's interface or documentation.
302
 
 
303
  - [CUDA runner and smoke protocol](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py)
304
  - [Document transformation and incremental output](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/document_run.py)
305
  - [Calibration, displacement math, hooks, and decoding](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/engine/steering.py)
 
3
  **William Taggart**
4
  Modern and Classical Languages and Literatures, Virginia Tech
5
  Email: wtaggart@vt.edu
6
+ **Technical report · November 14, 2026 · Revision 0.3**
7
 
8
  ## Abstract
9
 
10
+ AFFECTOR-ARC is an experimental text-rewriting system with a native macOS application and a command-line CUDA runner. The desktop application manages documents, emotional geometries, SSH connections, Slurm GPU jobs, and downloaded results; the runner executes a frozen Qwen3.5-0.8B model on an allocated ARC GPU. A trajectory specifies valence, inward/outward emotional orientation, and intensity across normalized document position. Contrasting English passages establish three activation directions at each selected transformer layer. During generation, trajectory coordinates determine a displacement scaled to the hidden-state magnitude, smoothed across decoding steps, and constrained by an RMS budget. Paired hooks apply it to the feed-forward input and residual path. Four editing styles, sentence-aware segmentation, bounded generation, and incremental reports make the intervention available within a document workflow. This report describes both interfaces and derives the steering mechanism, while distinguishing implementation checks from evidence of emotional effectiveness. Earlier desktop GPU runs and CPU policy tests are documented separately; they do not validate every subsequent runner revision or establish emotional accuracy, semantic preservation, or multilingual effectiveness.
11
 
12
  ## Purpose and Research Context
13
 
14
+ AFFECTOR-ARC investigates whether a writer can guide the emotional progression of a document by specifying a trajectory and intervening in a language model's internal computation. The practical aim is to make that experiment usable across a complete rewrite: the writer selects a text, supplies an emotional geometry, adjusts the intervention, and inspects the resulting passages and diagnostics. A native macOS application brings these activities into a workspace, while SSH and Slurm connect that workspace to a GPU allocation on Virginia Tech ARC. A command-line runner exposes the computation separately for scripted experiments and reproducible execution.
15
 
16
+ The geometry gives this workflow a common representation. It is an ordered path through valence, inward/outward emotional orientation, and intensity, accompanied by layer settings and optional calibration matrices. Sampling the path at successive document positions supplies the coordinates used during rewriting. Those coordinates become displacements of the model's hidden states, so the desired progression acts on the computation that produces tokens rather than prescribing particular words. The model's stored parameters remain fixed throughout.
17
+
18
+ This mechanism builds on contrastive activation steering. Turner and colleagues derive directions from contrasting prompts, and Panickssery and colleagues average differences between positive and negative behavioral examples ([Turner et al., 2023](https://arxiv.org/abs/2308.10248v1); [Panickssery et al., 2024](https://arxiv.org/abs/2312.06681v4)). AFFECTOR-ARC applies the same broad principle to small sets of emotionally contrasting passages, then mixes the resulting directions according to the requested trajectory. The central research question is how reliably this mapping can influence a sustained rewrite, given that a numerical displacement need not produce a unique or consistent emotional interpretation.
19
 
20
  ![Document workspace displaying an existing Little Red Riding Hood input and rewrite.](figures/screenshot-02.png)
21
 
22
  *Document workspace displaying an existing Little Red Riding Hood input and rewrite.*
23
 
24
+ That question connects the implementation to research on the relation between model representations and human judgments. Wu and colleagues study concept-based emotional steering across linguistic-cultural settings, while Diallo and colleagues use human ratings to examine perceived emotional intensity and text quality ([Wu et al., 2025](https://arxiv.org/abs/2506.13978v1); [Diallo et al., 2026](https://arxiv.org/abs/2601.21505v1)). These studies motivate coordinate-based experiments whose outcomes are judged through readers' interpretations. They do not, however, establish the validity of this system's inward/outward axis or calibrate its RMS-scaled controls. The requested trajectory, the activation displacement, and the emotion perceived in the output must therefore be evaluated as related but distinct quantities.
25
 
26
+ The reliability of that relationship also depends on where and how the intervention is applied. Shu and colleagues find uneven causal organization across emotion categories, and Wang and colleagues show that strong probing accuracy need not identify the most effective intervention layers ([Shu et al., 2026](https://arxiv.org/abs/2604.25866v3); [Wang et al., 2026](https://arxiv.org/abs/2609.22135v1)). Ha and colleagues' finding that supportive-empathy directions are only partially separable further cautions against treating emotional axes as independent controls ([Ha et al., 2026](https://arxiv.org/abs/2609.15654v1)). Automated vector extraction and context-dependent strength offer approaches to these calibration problems ([Cui et al., 2025](https://arxiv.org/abs/2509.22739v3); [Ferrando et al., 2025](https://arxiv.org/abs/2512.03661v2)). AFFECTOR-ARC makes layer weights and axis mixtures explicit so that such questions can be investigated, although its current runner uses user-selected settings rather than an adaptive emotional-feedback controller.
27
 
28
+ Applying those settings across a document makes generation stability part of the same problem. E-STEER reports non-monotonic effects of emotional interventions, and Jeong observes both emotional changes and degeneration in small models ([Sun et al., 2026](https://arxiv.org/abs/2604.00005v1); [Jeong, 2026](https://arxiv.org/abs/2604.04064v1)). A stronger displacement can thus disrupt a rewrite without bringing it closer to the intended trajectory. The system addresses the operational consequences through bounded generation, repetition checks, passage-level failure records, and a desktop workflow for reviewing jobs and results. These safeguards preserve an inspectable experiment; they do not establish that a completed rewrite meets its emotional target.
29
 
30
+ Evaluation must consequently consider emotional alignment together with fluency, content change, and failure rates. SteerScope examines efficacy, side effects, generalization, and dependence on steering data, finding no general advantage over prompt steering in its tested trade-offs ([Yang et al., 2026](https://arxiv.org/abs/2610.07722v1)). For AFFECTOR-ARC, this motivates comparisons with prompt-only and unsteered rewriting, blinded emotional and quality ratings, and complete reporting of retained originals, repetition, and truncation. The scope of this report is the desktop-to-cluster workflow and the implemented steering procedure, including their engineering checks. Establishing emotional effectiveness and a reliable operating range remains an empirical task.
31
 
32
  ## Runtime and data flow
33
 
34
+ ### Native macOS client and remote execution
35
+
36
+ The native SwiftUI application is distributed on Hugging Face for Apple Silicon Macs running macOS 15 or later. Its connection workspace configures SSH access and the Slurm resource request. The document workspace holds the input and generated text; the shape and weights workspace supports importing, converting, and editing geometries and intervention settings. Jobs and results controls expose remote progress, diagnostics, and output downloads. The application also manages Hugging Face source updates and submits GPU-environment setup through Slurm.
37
+
38
+ The Mac serves as the client: lightweight SSH requests manage files and jobs, while model setup and execution run in requested GPU allocations. The bundled Python remote agent handles requests over SSH without a persistent listening server. The desktop interface and the command-line runner are separately versioned components, so a recorded application version alone does not identify the remote engine revision. Both should be recorded when reporting a run.
39
+
40
+ ### CUDA runner
41
+
42
  The runner loads `Qwen/Qwen3.5-0.8B` at revision `2fc06364715b967f1860aea9cf38778875588b17`. The implementation uses `Qwen3_5ForConditionalGeneration`, its text decoder layers, float32 computation, eager attention, and the first process-visible CUDA device. It checks for 24 decoder layers; the geometry and calibration code assume hidden width 1,024. The backbone is in evaluation mode, its parameters have gradients disabled, and calibration and generation run without gradient tracking.
43
 
44
  ![Connection workspace with SSH settings and the Slurm GPU resource request. The client is offline in this capture.](figures/screenshot-01.png)
 
258
 
259
  JSON writes use temporary-file replacement. The companion text file is written normally and may be incomplete if interrupted during that write. Reports are incremental records, not automatic resume checkpoints: rerunning starts over and overwrites the selected output paths. Use a distinct output filename for each experiment. Reports contain the input text and should be treated as document-bearing artifacts.
260
 
261
+ The desktop document view is a presentation layer over these artifacts. The published client displays generated passages separately from source text and diagnostics; its text exports can therefore differ from the runner's assembled file, which includes retained originals. The downloadable report is needed to distinguish generated, retained, failed, and unprocessed passages. Reconnecting can recover an existing job and its outputs, but this client recovery does not make the runner's incremental report a resumable generation checkpoint.
262
+
263
  ## Engineering checks and evidence
264
 
265
  Smoke mode is the default and operates on one supplied passage. It runs baseline, zero-strength, positive-valence, negative-valence, and restored-baseline conditions. Positive and negative conditions use coefficient vectors $(0.8,0,0)$ and $(-0.8,0,0)$. The third coordinate zero corresponds to intensity 0.5.
 
270
 
271
  For the November 13 revision, seven CPU policy tests passed, Python and shell syntax were checked, and CLI loading was verified. Tests cover such behavior as unchanged requested controls, paragraph allowance accounting, draft retention, sentence cleanup, and continuing after a failed chunk. They do not execute the CUDA model. The current revision has not yet been run on an ARC GPU. A successful GPU run was reported for an earlier revision on November 12; it is historical evidence, not validation of the current code.
272
 
273
+ The desktop release also has its own validation record. Its published version 1.0.4 documentation reports native Swift tests, 14 remote-agent tests, a completed sample rewrite, and an earlier GPU setup on an NVIDIA A100-SXM4-80GB. These are release-specific engineering observations, not measurements of emotional accuracy or validation of later changes to the remote runner. The screenshots show the native application's workspaces, including offline states where indicated.
274
+
275
  ## Reproduction
276
 
277
+ For the desktop workflow, download the native macOS application from the repository's macos directory on Hugging Face, unpack it, and open AFFECTOR ARC.app. Configure the connection profile for the user's own ARC login, SSH authentication, and Slurm allocation. After connecting, install or update the remote source and prepare the GPU environment as needed. Import a document and geometry, adjust the settings, and choose Transform on ARC. Monitor the submitted job in Jobs + results and download its input, output, report, geometry, and logs. The published desktop README identifies the application as version 1.0.4 and describes its build as ad-hoc signed.
278
+
279
+ The following commands provide the separate command-line workflow. They run inside a suitable ARC GPU allocation from a fresh repository copy:
280
 
281
  ```bash
282
  bash setup.sh
 
314
 
315
  ## Implementation sources
316
 
317
+ This report covers the native macOS client, its SSH request agent, and the CUDA runner. The desktop release and its source are available alongside the remote engine:
318
 
319
+ - [Native macOS application, Swift source, and release documentation](https://huggingface.co/will-taggart/AFFECTOR-ARC/tree/main/macos)
320
  - [CUDA runner and smoke protocol](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/run_arc.py)
321
  - [Document transformation and incremental output](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/document_run.py)
322
  - [Calibration, displacement math, hooks, and decoding](https://huggingface.co/will-taggart/AFFECTOR-ARC/blob/main/engine/steering.py)