Rename AFFECTOR paper and remove verification screenshot

.gitattributes

@@ -43,3 +43,5 @@ paper/figures/screenshot-02.png filter=lfs diff=lfs merge=lfs -text
 paper/figures/screenshot-03.png filter=lfs diff=lfs merge=lfs -text
 paper/figures/screenshot-04.png filter=lfs diff=lfs merge=lfs -text
 paper/figures/screenshot-05.png filter=lfs diff=lfs merge=lfs -text
+paper/AFFECTOR.pdf filter=lfs diff=lfs merge=lfs -text
+docs/AFFECTOR.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -9,7 +9,7 @@ inference: false
 language:
 - en
 ---
-**Technical paper:** [PDF](paper/AFFECTOR-ACM.pdf) · [LaTeX source](paper/AFFECTOR-ACM.tex) · [Complete source ZIP](paper/AFFECTOR-ACM-source.zip) · [Markdown](paper/TECHNICAL_PAPER.md) · [Figures and source](paper/)
+**Technical paper:** [PDF](paper/AFFECTOR.pdf) · [LaTeX source](paper/AFFECTOR.tex) · [Complete source ZIP](paper/AFFECTOR-source.zip) · [Markdown](paper/TECHNICAL_PAPER.md) · [Figures and source](paper/)
 
 # AFFECTOR
 
@@ -23,7 +23,7 @@ language:
 
 Unzip, move **AFFECTOR.app** into **Applications**, and launch it. Local generation works offline with no separate Python installation, model download, or API account.
 
-[Read the technical paper (PDF)](docs/AFFECTOR-Technical-Paper.pdf) · [Browse all files](https://huggingface.co/will-taggart/AFFECTOR/tree/main) · [Verify checksums](SHA256SUMS.txt) · [Apple release status](RELEASE_STATUS.md)
+[Read the technical paper (PDF)](docs/AFFECTOR.pdf) · [Browse all files](https://huggingface.co/will-taggart/AFFECTOR/tree/main) · [Verify checksums](SHA256SUMS.txt) · [Apple release status](RELEASE_STATUS.md)
 
 **Emotional trajectories for text rewriting**
 
@@ -76,7 +76,7 @@ Generation uses sentence-aware chunks of up to 700 characters. Output aims for t
 
 ## Files and reproducibility
 
-- [Technical paper (PDF)](docs/AFFECTOR-Technical-Paper.pdf) and [Markdown source](docs/TECHNICAL_PAPER.md): representation, calibration, equations, generation, verification, evidence and limitations, explained from first principles.
+- [Technical paper (PDF)](docs/AFFECTOR.pdf) and [Markdown source](docs/TECHNICAL_PAPER.md): representation, calibration, equations, generation, verification, evidence and limitations, explained from first principles.
 - [Apple release guide](docs/APPLE_RELEASE.md): signing, notarization, stapling, and verification.
 - `source/`: the current engine, SwiftUI app, build/signing utilities, and tests.
 - `SHA256SUMS.txt`: checksums of the downloadable app and source archive.

docs/{AFFECTOR-Technical-Paper.pdf → AFFECTOR.pdf}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e059179343c7acd54f1d6b8da8ba36cdb0fe941aca291f9be6d9bf4aa5a9dd0b
-size 2131283
+oid sha256:d7b7e0a6f4b72c7977f1057accfe011d99c49c39dd70f3ce8d197a11b7efba36
+size 1954963

docs/TECHNICAL_PAPER.md

@@ -1,6 +1,6 @@
 # AFFECTOR: Coordinate-Guided Text Rewriting through Transformer Activation Interventions
 
-**Technical paper:** [PDF](AFFECTOR-ACM.pdf) · [LaTeX source](AFFECTOR-ACM.tex) · [Complete source ZIP](AFFECTOR-ACM-source.zip)
+**Technical paper:** [PDF](../paper/AFFECTOR.pdf) · [LaTeX source](../paper/AFFECTOR.tex) · [Complete source ZIP](../paper/AFFECTOR-source.zip)
 
 **William Taggart**  
 Modern and Classical Languages and Literatures, Virginia Tech  
@@ -141,9 +141,7 @@ These mechanisms trade completeness for bounded readable output. Sentence punctu
 
 Verification assesses original and revised chunks separately with an unsteered evaluator or an API model. The evaluator is instructed to distinguish felt or conveyed emotion from mere emotion-word occurrence, identify experiencers and emotional targets, and supply exact quoted evidence. It returns valence, direction, intensity, emotional labels, uncertainty, and concise explanations. Scores are interpretive estimates, not psychometric measurements.
 
-![Verification controls before evaluation. No verification results have been computed in this view.](../paper/figures/screenshot-05.png)
 
-*Verification controls before evaluation. No verification results have been computed in this view.*
 For assessed coordinate `p=(v,d,2i-1)` and target `c`, the reported similarity is:
 
 `similarity = 1 - ||p-c||_2 / (2 sqrt(3))`.

docs/TECHNICAL_REPORT.md

@@ -1,6 +1,6 @@
 # AFFECTOR: Coordinate-Guided Text Rewriting through Transformer Activation Interventions
 
-**Technical paper:** [PDF](AFFECTOR-ACM.pdf) · [LaTeX source](AFFECTOR-ACM.tex) · [Complete source ZIP](AFFECTOR-ACM-source.zip)
+**Technical paper:** [PDF](../paper/AFFECTOR.pdf) · [LaTeX source](../paper/AFFECTOR.tex) · [Complete source ZIP](../paper/AFFECTOR-source.zip)
 
 **William Taggart**  
 Modern and Classical Languages and Literatures, Virginia Tech  
@@ -141,9 +141,7 @@ These mechanisms trade completeness for bounded readable output. Sentence punctu
 
 Verification assesses original and revised chunks separately with an unsteered evaluator or an API model. The evaluator is instructed to distinguish felt or conveyed emotion from mere emotion-word occurrence, identify experiencers and emotional targets, and supply exact quoted evidence. It returns valence, direction, intensity, emotional labels, uncertainty, and concise explanations. Scores are interpretive estimates, not psychometric measurements.
 
-![Verification controls before evaluation. No verification results have been computed in this view.](../paper/figures/screenshot-05.png)
 
-*Verification controls before evaluation. No verification results have been computed in this view.*
 For assessed coordinate `p=(v,d,2i-1)` and target `c`, the reported similarity is:
 
 `similarity = 1 - ||p-c||_2 / (2 sqrt(3))`.

paper/AFFECTOR-ACM.source.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14
-size 6603309

paper/AFFECTOR-Technical-Report-ACM-source.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14
-size 6603309

paper/AFFECTOR-Technical-Report-ACM.bbl

@@ -1,264 +0,0 @@
-%%% -*-BibTeX-*-
-%%% Do NOT edit. File created by BibTeX with style
-%%% ACM-Reference-Format-Journals [18-Jan-2012].
-
-\begin{thebibliography}{12}
-
-%%% ====================================================================
-%%% NOTE TO THE USER: you can override these defaults by providing
-%%% customized versions of any of these macros before the \bibliography
-%%% command.  Each of them MUST provide its own final punctuation,
-%%% except for \shownote{}, \showDOI{}, and \showURL{}.  The latter two
-%%% do not use final punctuation, in order to avoid confusing it with
-%%% the Web address.
-%%%
-%%% To suppress output of a particular field, define its macro to expand
-%%% to an empty string, or better, \unskip, like this:
-%%%
-%%% \newcommand{\showDOI}[1]{\unskip}   % LaTeX syntax
-%%%
-%%% \def \showDOI #1{\unskip}           % plain TeX syntax
-%%%
-%%% ====================================================================
-
-\ifx \showCODEN    \undefined \def \showCODEN     #1{\unskip}     \fi
-\ifx \showDOI      \undefined \def \showDOI       #1{#1}\fi
-\ifx \showISBNx    \undefined \def \showISBNx     #1{\unskip}     \fi
-\ifx \showISBNxiii \undefined \def \showISBNxiii  #1{\unskip}     \fi
-\ifx \showISSN     \undefined \def \showISSN      #1{\unskip}     \fi
-\ifx \showLCCN     \undefined \def \showLCCN      #1{\unskip}     \fi
-\ifx \shownote     \undefined \def \shownote      #1{#1}          \fi
-\ifx \showarticletitle \undefined \def \showarticletitle #1{#1}   \fi
-\ifx \showURL      \undefined \def \showURL       {\relax}        \fi
-% The following commands are used for tagged output and should be
-% invisible to TeX
-\providecommand\bibfield[2]{#2}
-\providecommand\bibinfo[2]{#2}
-\providecommand\natexlab[1]{#1}
-\providecommand\showeprint[2][]{arXiv:#2}
-
-\bibitem[Cui and Chen(2025)]%
-        {cui2025pas}
-\bibfield{author}{\bibinfo{person}{Sasha Cui} {and} \bibinfo{person}{Zhongren
-  Chen}.} \bibinfo{year}{2025}\natexlab{}.
-\newblock \bibinfo{title}{{Painless Activation Steering: An Automated,
-  Lightweight Approach for Post-Training Large Language Models}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2509.22739v3}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2509.22739v3}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-05-15; metadata checked 2026-11-13}.
-
-
-\bibitem[Diallo et~al\mbox{.}(2026)]%
-        {diallo2026style}
-\bibfield{author}{\bibinfo{person}{Diaoulé Diallo}, \bibinfo{person}{Katharina
-  Dworatzyk}, \bibinfo{person}{Sophie Jentzsch}, \bibinfo{person}{Peer
-  Schütt}, \bibinfo{person}{Sabine Theis}, {and} \bibinfo{person}{Tobias
-  Hecking}.} \bibinfo{year}{2026}\natexlab{}.
-\newblock \bibinfo{title}{{The Effectiveness of Style Vectors for Steering
-  Large Language Models: A Human Evaluation}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2601.21505v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2601.21505v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-01-29; metadata checked 2026-11-13}.
-
-
-\bibitem[Ferrando et~al\mbox{.}(2025)]%
-        {ferrando2025dsas}
-\bibfield{author}{\bibinfo{person}{Alex Ferrando}, \bibinfo{person}{Xavier
-  Suau}, \bibinfo{person}{Jordi Gonzàlez}, {and} \bibinfo{person}{Pau
-  Rodriguez}.} \bibinfo{year}{2025}\natexlab{}.
-\newblock \bibinfo{title}{{Dynamically Scaled Activation Steering}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2512.03661v2}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2512.03661v2}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-07-30; metadata checked 2026-11-13}.
-
-
-\bibitem[Ha et~al\mbox{.}(2026)]%
-        {ha2026empathy}
-\bibfield{author}{\bibinfo{person}{JuHeon Ha}, \bibinfo{person}{Byounghan Lee},
-  \bibinfo{person}{Yunseo Choi}, {and} \bibinfo{person}{Kyung-Ah Sohn}.}
-  \bibinfo{year}{2026}\natexlab{}.
-\newblock \bibinfo{title}{{Empathy Is Steerable but Multi-Axial: Mechanism
-  Geometry and Persona Effects in LLMs}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2609.15654v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2609.15654v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-09-14; metadata checked 2026-11-13}.
-
-
-\bibitem[Jeong(2026)]%
-        {jeong2026emotion}
-\bibfield{author}{\bibinfo{person}{Jihoon Jeong}.}
-  \bibinfo{year}{2026}\natexlab{}.
-\newblock \bibinfo{title}{{Extracting and Steering Emotion Representations in
-  Small Language Models: A Methodological Comparison}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2604.04064v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2604.04064v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-04-05; metadata checked 2026-11-13}.
-
-
-\bibitem[Panickssery et~al\mbox{.}(2024)]%
-        {panickssery2024caa}
-\bibfield{author}{\bibinfo{person}{Nina Panickssery}, \bibinfo{person}{Nick
-  Gabrieli}, \bibinfo{person}{Julian Schulz}, \bibinfo{person}{Meg Tong},
-  \bibinfo{person}{Evan Hubinger}, {and} \bibinfo{person}{Alexander~Matt
-  Turner}.} \bibinfo{year}{2024}\natexlab{}.
-\newblock \bibinfo{title}{{Steering Llama 2 via Contrastive Activation
-  Addition}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2312.06681v4}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2312.06681v4}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2024-07-05; metadata checked 2026-11-13}.
-
-
-\bibitem[Shu et~al\mbox{.}(2026)]%
-        {shu2026emotion}
-\bibfield{author}{\bibinfo{person}{Bangzhao Shu}, \bibinfo{person}{Arinjay
-  Singh}, {and} \bibinfo{person}{Mai ElSherief}.}
-  \bibinfo{year}{2026}\natexlab{}.
-\newblock \bibinfo{title}{{Why Are Some Emotions Harder for LLMs? Uncovering
-  the Causal Mechanisms of Emotion Inference via Sparse Autoencoders}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2604.25866v3}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2604.25866v3}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-10-24; metadata checked 2026-11-13}.
-
-
-\bibitem[Sun et~al\mbox{.}(2026)]%
-        {sun2026emotion}
-\bibfield{author}{\bibinfo{person}{Moran Sun}, \bibinfo{person}{Tianlin Li},
-  \bibinfo{person}{Yuwei Zheng}, \bibinfo{person}{Zhenhong Zhou},
-  \bibinfo{person}{Aishan Liu}, \bibinfo{person}{Xianglong Liu}, {and}
-  \bibinfo{person}{Yang Liu}.} \bibinfo{year}{2026}\natexlab{}.
-\newblock \bibinfo{title}{{How Emotion Shapes the Behavior of LLMs and Agents:
-  A Mechanistic Study}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2604.00005v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2604.00005v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-03-09; metadata checked 2026-11-13}.
-
-
-\bibitem[Turner et~al\mbox{.}(2023)]%
-        {turner2023actadd}
-\bibfield{author}{\bibinfo{person}{Alex Turner}, \bibinfo{person}{Lisa
-  Thiergart}, \bibinfo{person}{David Udell}, \bibinfo{person}{Gavin Leech},
-  \bibinfo{person}{Ulisse Mini}, {and} \bibinfo{person}{Monte MacDiarmid}.}
-  \bibinfo{year}{2023}\natexlab{}.
-\newblock \bibinfo{title}{{Activation Addition: Steering Language Models
-  Without Optimization}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2308.10248v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2308.10248v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2023-08-20; metadata checked 2026-11-13}.
-
-
-\bibitem[Wang et~al\mbox{.}(2026)]%
-        {wang2026readbest}
-\bibfield{author}{\bibinfo{person}{Yibo Wang}, \bibinfo{person}{Jisheng Dang},
-  \bibinfo{person}{Bimei Wang}, \bibinfo{person}{Yitao Wu},
-  \bibinfo{person}{Wencan Zhang}, \bibinfo{person}{Hong Peng},
-  \bibinfo{person}{Jizhao Liu}, \bibinfo{person}{Bin Hu}, \bibinfo{person}{Qi
-  Tian}, {and} \bibinfo{person}{Tat-Seng Chua}.}
-  \bibinfo{year}{2026}\natexlab{}.
-\newblock \bibinfo{title}{{Read-Best Is Not Steer-Best: A Probing--Steering
-  Layer Dissociation in Omni-Modal Large Language Models}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2609.22135v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2609.22135v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-08-24; metadata checked 2026-11-13}.
-
-
-\bibitem[Wu et~al\mbox{.}(2025)]%
-        {wu2025emotion}
-\bibfield{author}{\bibinfo{person}{Xiuwen Wu}, \bibinfo{person}{Hao Wang},
-  \bibinfo{person}{Zhiang Yan}, \bibinfo{person}{Xiaohan Tang},
-  \bibinfo{person}{Pengfei Xu}, \bibinfo{person}{Wai-Ting Siok},
-  \bibinfo{person}{Ping Li}, \bibinfo{person}{Jia-Hong Gao},
-  \bibinfo{person}{Bingjiang Lyu}, {and} \bibinfo{person}{Lang Qin}.}
-  \bibinfo{year}{2025}\natexlab{}.
-\newblock \bibinfo{title}{{AI shares emotion with humans across languages and
-  cultures}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2506.13978v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2506.13978v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2025-06-11; metadata checked 2026-11-13}.
-
-
-\bibitem[Yang et~al\mbox{.}(2026)]%
-        {yang2026steerscope}
-\bibfield{author}{\bibinfo{person}{Haotian Yang}, \bibinfo{person}{Huikang
-  Jiang}, \bibinfo{person}{Yucheng Wu}, \bibinfo{person}{Wen-Jie Jiang},
-  \bibinfo{person}{Chenpeng Wang}, \bibinfo{person}{Yibin Lou}, {and}
-  \bibinfo{person}{Liangming Pan}.} \bibinfo{year}{2026}\natexlab{}.
-\newblock \bibinfo{title}{{Does Steering Break Your Model? A Multi-Dimensional
-  Evaluation Suite for LLM Steering Methods}}.
-\newblock
-\newblock
-\showeprint[arxiv]{2610.07722v1}
-\urldef\tempurl%
-\url{https://arxiv.org/abs/2610.07722v1}
-\showURL{%
-\tempurl}
-\newblock
-\shownote{Cited version dated 2026-10-06; metadata checked 2026-11-13}.
-
-
-\end{thebibliography}

paper/AFFECTOR-Technical-Report-ACM.pdf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e059179343c7acd54f1d6b8da8ba36cdb0fe941aca291f9be6d9bf4aa5a9dd0b
-size 2131283

paper/AFFECTOR-Technical-Report-ACM.source.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14
-size 6603309

paper/AFFECTOR-Technical-Report-ACM.tex

@@ -1,542 +0,0 @@
-% Layout for an independently distributed technical report.
-\documentclass[manuscript,screen,nonacm]{acmart}
-\setcopyright{none}
-\settopmatter{printacmref=false,printccs=false}
-\acmDOI{}
-\acmISBN{}
-\usepackage{longtable,booktabs,array,calc}
-\usepackage{xurl}
-\usepackage{fvextra}
-\DefineVerbatimEnvironment{verbatim}{Verbatim}{breaklines=true,fontsize=\small}
-\usepackage{tikz}
-\usetikzlibrary{positioning}
-\providecommand{\tightlist}{\setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}
-\providecommand{\passthrough}[1]{#1}
-\providecommand{\pandocbounded}[1]{#1}
-\usepackage{graphicx,float}
-
-% Permit figures to share pages with surrounding explanatory text.
-\renewcommand{\topfraction}{0.92}
-\renewcommand{\bottomfraction}{0.85}
-\renewcommand{\textfraction}{0.06}
-\renewcommand{\floatpagefraction}{0.80}
-\setcounter{topnumber}{3}
-\setcounter{bottomnumber}{3}
-\setcounter{totalnumber}{5}
-\setlength{\textfloatsep}{12pt plus 2pt minus 3pt}
-\setlength{\intextsep}{12pt plus 2pt minus 3pt}
-\raggedbottom
-
-\geometry{top=0.75in,bottom=0.65in,includeheadfoot}
-\begin{document}
-\title{AFFECTOR: Coordinate-Guided Text Rewriting through Transformer
-Activation Interventions}
-\author{William Taggart}
-\affiliation{\department{Modern and Classical Languages and Literatures}
-\institution{Virginia Tech}\city{Blacksburg}\state{Virginia}\country{USA}}
-\email{wtaggart@vt.edu}
-\subtitle{Technical Report: November 13, 2026}
-\begin{abstract}
-AFFECTOR investigates whether a prescribed emotional trajectory can
-influence the rewriting of a document. A trajectory assigns valence,
-emotional direction, and intensity to normalized positions in a text. A
-local backend maps these coordinates into perturbations of a frozen
-language model's internal states, while hosted backends use
-coordinate-bearing instructions. The desktop application supports
-geometry authoring, editable numerical steering matrices, document
-conversion, checkpointing, and separate emotional verification. This
-paper derives the implemented method from first principles and
-distinguishes mechanical correctness from successful emotional transfer.
-Current controls can produce emotionally charged language but can also
-produce weak paraphrases, factual distortions, and repetition. The
-implementation is an experimental instrument, not a validated predictor
-or controller of human emotion.
-\end{abstract}
-\keywords{activation steering, emotional text generation, transformer models, controllable generation}
-\maketitle
-\section{Literature review: activation steering and
-emotion}\label{literature-review-activation-steering-and-emotion}
-
-This focused review covers twelve papers, emphasizing 2025-2026 research
-and retaining two methodological foundations. Titles, author lists,
-version histories, and the claims summarized here were checked against
-arXiv records and the corresponding paper text on November 13, 2026. The
-cited versions are fixed below; availability on arXiv alone does not
-establish peer review. The implications for this project are research
-motivations, not evidence that its implementation reproduces these
-results.
-
-\textbf{From activation differences to behavioral control.} Activation
-steering changes internal model states during inference while leaving
-the backbone weights fixed. Turner et al.~derive intervention vectors
-from contrasting prompts; Panickssery et al.~average differences across
-positive and negative behavioral examples. These provide the
-methodological basis for contrastive calibration, but do not validate a
-particular emotional coordinate system or insertion site.
-\citep{turner2023actadd}; \citep{panickssery2024caa}.
-
-\textbf{Emotional expression and human judgment.} Wu et al.~relate model
-emotion spaces to human valence/arousal judgments and report
-concept-based steering across linguistic-cultural settings. Diallo et
-al.~evaluate perceived emotional intensity and text quality with human
-raters, finding that effects depend on emotion and steering strength.
-Together they motivate separate measures of emotional movement and
-readability. Their axes and numerical strengths cannot be assumed
-equivalent to this project's inward/outward direction or RMS-scaled
-controls. \citep{wu2025emotion}; \citep{diallo2026style}.
-
-\textbf{Emotion can affect more than tone.} Sun et al.'s E-STEER uses
-valence-arousal-dominance interventions to study reasoning, generation,
-safety, and agent behavior, reporting non-monotonic relationships.
-Jeong's small-model comparison reports both coherent emotional changes
-and degeneration, including repetition, depending on extraction method
-and architecture. These findings motivate reporting failed generations
-alongside successes and testing strength sweeps rather than assuming
-that larger perturbations improve emotional fit. Neither study
-establishes an operating range for this implementation.
-\citep{sun2026emotion}; \citep{jeong2026emotion}.
-
-\textbf{Reading an emotion is different from controlling it.} Shu et
-al.'s revised study identifies uneven causal organization of sparse
-features across emotion categories and tests interventions for emotion
-recognition. Wang et al.~show, in omni-modal models, that layers with
-strong emotion-probing accuracy need not be the best intervention
-layers. Recognition results therefore inform evaluator design, while
-layer selection for rewriting still requires causal tests on generated
-text. Neither finding licenses importing layer indices across
-architectures. \citep{shu2026emotion}; \citep{wang2026readbest}.
-
-\textbf{Multiple axes and adaptive control.} Ha et al.~find that
-supportive-empathy directions are only partially separable: intervening
-on one can shift other EPITOME proxy scores. Cui and Chen automate
-vector extraction from labeled data, with task-dependent benefits.
-Ferrando et al.~adapt intervention strength to context, studying the
-balance between toxicity mitigation and retained utility. These
-approaches motivate broader calibration, cross-axis tests, and future
-adaptive control. The present coordinate mixture is not an
-implementation of their learned selectors or context-dependent gates.
-\citep{ha2026empathy}; \citep{cui2025pas}; \citep{ferrando2025dsas}.
-
-\textbf{Evaluation must include costs as well as target effects.} Yang
-et al.'s SteerScope evaluates steering efficacy jointly with side
-effects, generalization, and data dependence. In its tested settings,
-activation methods do not dominate prompt steering on the
-efficacy/side-effect trade-off. For this project, the resulting
-evaluation priorities are prompt-only and unsteered baselines, blinded
-emotional and quality ratings, content-change assessment appropriate to
-the rewrite style, and complete accounting of repetition, truncation,
-and original-text fallbacks. This is an evaluation agenda, not a
-completed benchmark. \citep{yang2026steerscope}.
-
-
-\section{Problem formulation}\label{problem-formulation}
-
-
-\begin{figure}[!htb]
-\centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-01.png}
-\caption{Document workspace with an example input, rewrite controls, and an empty output pane before generation.}
-\Description{Document workspace with an example input, rewrite controls, and an empty output pane before generation.}
-\label{fig:app-screen-1}
-\end{figure}
-A document conveys more than propositions: lexical choice, focus,
-rhythm, imagery, and narrative stance can contribute to an emotional
-reading. Rewriting a document to follow a desired emotional progression
-is consequently a multi-objective problem. The output should express the
-requested affect, remain readable, retain whatever content its rewrite
-style requires, and have a manageable length. These objectives can
-conflict.
-
-AFFECTOR represents the desired affect as an ordered curve, not a
-vocabulary list. A curve does not uniquely determine a text: countless
-passages can share the same coarse coordinates. The application offers
-two mechanisms to bias generation toward that curve. Local activation
-intervention changes numerical states during inference. API prompting
-describes the desired coordinates to a remote model. These mechanisms
-are not equivalent, and their results should be evaluated separately.
-
-The current system does not solve a constrained optimization problem
-over complete texts. In particular, it does not automatically measure a
-generated passage and iteratively minimize its emotional distance.
-Verification is an explicit later operation.
-
-\section{Representation and
-alignment}\label{representation-and-alignment}
-
-
-\begin{figure}[!htb]
-\centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-02.png}
-\caption{Geometry editor showing the selected three-point trajectory and its steering controls.}
-\Description{Geometry editor showing the selected three-point trajectory and its steering controls.}
-\label{fig:app-screen-2}
-\end{figure}
-A geometry consists of ordered points \nolinkurl{(t, v, d, i)}. Position
-\nolinkurl{t} is in \texttt{{[}0,1{]}}; valence \nolinkurl{v} and direction
-\nolinkurl{d} are in \texttt{{[}-1,1{]}}; intensity \nolinkurl{i} is in
-\texttt{{[}0,1{]}}. Negative valence denotes unpleasant affect and
-positive valence pleasant affect. Negative direction denotes
-self-focused or inward-directed emotion; positive direction denotes
-outward focus. Direction is independent of valence: anger toward oneself
-can be inward and sadness for another person outward. Intensity
-describes strength of affect, not pleasantness.
-
-For intervention, intensity is centered:
-
-\[c(t)=(v(t),d(t),2i(t)-1).\]
-
-Coordinates are linearly interpolated between points, with endpoint
-clamping outside the stored range. Geometry imports that lack a
-supported direction omit that point; interpolating across the resulting
-gap can smooth away meaningful transitions. The imported data's
-provenance records incomplete coverage.
-
-The target document is divided into chunks of at most 700 characters,
-preferring sentence endings and then whitespace. Blank-line paragraph
-boundaries, including whitespace-only blank lines, are recognized. If a
-chunk spans original character offsets \nolinkurl{a} through \nolinkurl{b} in
-an input of length \nolinkurl{N}, its target position is
-\nolinkurl{(a+b)/(2N)}. This is computed from the original document, so
-expansion of earlier output does not move later targets. A single
-coordinate is applied throughout a chunk. Neighboring chunks are
-generated independently without surrounding text as generation context.
-
-This normalized alignment compresses or stretches a source trajectory to
-the target length. It samples only as many positions as there are
-chunks. It does not preserve all events or oscillations of a much longer
-curve. Changes to segmentation can change emotional targets even when
-the same geometry is selected.
-
-\begin{figure}[!htb]
-\centering
-\includegraphics[width=\textwidth]{figures/illustration-01.pdf}
-\caption{Normalized alignment schematic. Target chunks sample a continuous source path at original character midpoints; a short target can miss narrow changes in a long source trajectory.}
-\Description{One continuous path, a finite set of targets. Normalized alignment schematic. Target chunks sample a continuous source path at original character midpoints; a short target can miss narrow changes in a long source trajectory.}
-\label{fig:illustration-1}
-\end{figure}
-
-\section{Frozen model and contrastive
-calibration}\label{frozen-model-and-contrastive-calibration}
-
-
-\begin{figure}[!htb]
-\centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-03.png}
-\caption{Source-analysis dialog for generating a geometry and optionally calibrating a local activation basis.}
-\Description{Source-analysis dialog for generating a geometry and optionally calibrating a local activation basis.}
-\label{fig:app-screen-3}
-\end{figure}
-The local backend loads Qwen3.5-0.8B at revision
-\nolinkurl{2fc06364715b967f1860aea9cf38778875588b17}. The implementation
-operates on its text stack of 24 blocks with hidden width 1,024. Base
-parameters are frozen; inference uses float32 and eager attention. Apple
-MPS is selected when available, otherwise CPU. The chat template
-disables thinking output. The package contains Python 3.14, PyTorch
-2.15.0 and Transformers 5.22.2; exact dependency pins accompany the
-bundle.
-
-Before steering, the application obtains three directions per selected
-layer from twelve manually authored English contrast pairs, four per
-axis. For example, valence pairs contrast despair with joy, and
-intensity pairs contrast mild unease with overwhelming terror. Both
-members of every pair are processed under a continuation instruction.
-Thus calibration requires 24 forward passes.
-
-The capture site is the final chat-formatted prompt position immediately
-before the post-attention normalization that feeds the feed-forward
-sublayer. It is not a mean over all content tokens. For layer \nolinkurl{l}
-and axis \nolinkurl{j}, the mean contrast is:
-
-\[u_{\ell,j}=\frac14\sum_k(h^+_{\ell,j,k}-h^-_{\ell,j,k}).\]
-
-With \texttt{RMS(x)\ =\ sqrt(mean\_r(x{[}r{]}\^{}2))}, normalization
-gives:
-
-\[B_{\ell,j}=\frac{u_{\ell,j}}{\max(\operatorname{RMS}(u_{\ell,j}),10^{-8})}.\]
-
-The resulting \texttt{B{[}l{]}} is a 3 by 1,024 matrix. These are the
-editable steering-module weights. Defaults select layers 8, 16, and 23,
-with weights 1, 1, and 0.5. Geometry files retain the calibration
-examples, matrices, and model/runtime identity; incompatible identities
-are rejected.
-
-There is no gradient training, score-supervised fitting,
-orthogonalization, or guarantee that the three directions isolate their
-intended concepts. Small hand-authored pairs can confound affect with
-genre, topic, lexical content, and emotional categories. Calibration is
-exploratory and English-based; multilingual effectiveness has not been
-established.
-
-
-\section{Coordinate-to-activation
-computation}\label{coordinate-to-activation-computation}
-
-
-\begin{figure}[!htb]
-\centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-04.png}
-\caption{Expanded numerical weights for the selected geometry, including the local calibration metadata.}
-\Description{Expanded numerical weights for the selected geometry, including the local calibration metadata.}
-\label{fig:app-screen-4}
-\end{figure}
-Axis temperature \nolinkurl{T} transforms each coordinate magnitude while
-retaining its sign:
-
-\[q_j=\operatorname{sign}(c_j)|c_j|^{1/T}.\]
-
-The implementation ranks axes by magnitude, retains at most axis top-k,
-and stops adding axes once cumulative magnitude reaches the configured
-mass fraction. Surviving coefficients are not renormalized. These
-operations act on three emotional coefficients, not on the model's
-vocabulary distribution.
-
-For current final-token hidden state \nolinkurl{h}, strength \nolinkurl{s},
-and layer weight \texttt{w{[}l{]}}, the proposed perturbation is:
-
-\[\delta_{\mathrm{raw}}=(q B_\ell)\operatorname{RMS}(h)s w_\ell.\]
-
-Inertia \nolinkurl{rho} combines this proposal with the previous applied
-perturbation within the same chunk:
-
-\[\delta_{\mathrm{mix}}=\rho\delta_{\mathrm{previous}}+(1-\rho)\delta_{\mathrm{raw}}.\]
-
-The first step uses the raw proposal directly. A relative RMS budget
-\nolinkurl{beta} then bounds the perturbation:
-
-\[\delta=\delta_{\mathrm{mix}}\min\left(1,\frac{\beta\operatorname{RMS}(h)}{\max(\operatorname{RMS}(\delta_{\mathrm{mix}}),10^{-12})}\right).\]
-
-Zero strength, budget, or layer weight gives an exact zero perturbation.
-Each chunk resets inertia history. The settings are applied as
-requested; the release does not automatically lower them after poor
-output.
-
-Budget is not a semantic-change percentage. At budget 1, the
-perturbation can have RMS magnitude comparable to the original hidden
-state at that site. Large values can destabilize generation. Raising the
-budget only matters when the proposed perturbation would otherwise be
-clipped; it cannot correct an inaccurate direction.
-
-
-\section{Intervention within the
-transformer}\label{intervention-within-the-transformer}
-
-Let \nolinkurl{h} denote a block's residual state after its attention or
-sequence-mixing stage. A conventional feed-forward residual update has
-the form:
-
-\[y=h+\operatorname{FFN}(\operatorname{Norm}(h)).\]
-
-AFFECTOR implements:
-
-\[y=(h+\delta)+\operatorname{FFN}(\operatorname{Norm}(h+\delta)).\]
-
-A pre-hook on the feed-forward normalization adds \nolinkurl{delta} to its
-input, and a post-hook on the block output adds the same \nolinkurl{delta}
-to the residual branch. This is a forward-pass intervention, not a
-model-parameter update. Hooks affect only the final token in the initial
-prompt pass and the current token during cached decoding. They are
-removed when generation exits, including exceptional exits.
-
-The module does not search for trigger phrases or recognize an idiom
-before activating. The chosen target determines the intervention
-continuously during decoding. Nevertheless, generation remains
-conditional on the input and instruction, and the hidden state
-influences perturbation magnitude. The module is not a
-content-independent guarantee of a particular affect.
-
-A key limitation is that the intervention is an absolute-coordinate
-bias, not a measured error correction. A target valence of zero yields
-no direct valence-axis perturbation; it does not actively neutralize an
-already negative passage. Correlations between basis vectors further
-complicate interpretation.
-
-
-\section{Prompts, sampling, and bounded
-output}\label{prompts-sampling-and-bounded-output}
-
-Four rewrite styles constrain the instruction: Minimal preserves nearly
-all wording; Restrained asks for subtle emotional phrasing changes while
-preserving facts and structure; Balanced allows structural changes and
-modest imagery while preserving events; Creative permits changes to
-meaning, imagery, and events. The prompt preferences do not enforce
-semantic fidelity.
-
-Local prompts do not include the numerical emotional coordinates. Hosted
-prompts do, because hosted model hidden states are not accessible
-through the implemented APIs. Consequently, local and API modes are not
-controlled comparisons of model size alone.
-
-Temperature, top-p, and top-k govern token selection. At temperature
-zero, decoding is greedy and top-p/top-k are inactive. Positive
-temperature enables sampling. A repetition penalty of 1.1 and no-repeat
-8-gram constraint operate on token decoding; they are distinct from
-activation steering and cannot guarantee freedom from repetition.
-
-The current output policy uses a shared paragraph allowance equal to
-125\% of original character length. Unused allowance carries forward to
-later chunks in the same paragraph; original intervening whitespace
-counts against it. Earlier chunks cannot borrow from future chunks.
-Local generation seeks a sentence ending after 85\% of the current
-original chunk length. A hard character ceiling, token ceiling, and
-120-second limit remain. Token allowances may expand above the displayed
-base allowance, up to 2,048 locally and 4,096 for hosted requests.
-
-Repetition detection inspects recent word n-grams and repeated character
-patterns. If a draft is repetitive, oversized, or unfinished, the output
-can retain only its complete, non-repetitive sentence prefix, with a
-warning. If no such prefix exists, the original is retained with an
-error. One generation attempt is made per chunk; returned drafts,
-effective controls, stop reasons, and selection information remain in
-reports. API calls are non-streaming, so their remote generation cannot
-be stopped at an exact character threshold.
-
-These mechanisms trade completeness for bounded readable output.
-Sentence punctuation is a heuristic and can misidentify abbreviations or
-unusual writing. Trimming can omit important content and alter emotional
-character. They are safeguards against specific generation failures, not
-a proof of success.
-
-\section{Independent verification}\label{independent-verification}
-
-
-\begin{figure}[!htb]
-\centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-05.png}
-\caption{Verification controls before evaluation. No verification results have been computed in this view.}
-\Description{Verification controls before evaluation. No verification results have been computed in this view.}
-\label{fig:app-screen-5}
-\end{figure}
-Verification assesses original and revised chunks separately with an
-unsteered evaluator or an API model. The evaluator is instructed to
-distinguish felt or conveyed emotion from mere emotion-word occurrence,
-identify experiencers and emotional targets, and supply exact quoted
-evidence. It returns valence, direction, intensity, emotional labels,
-uncertainty, and concise explanations. Scores are interpretive
-estimates, not psychometric measurements.
-
-For assessed coordinate \nolinkurl{p=(v,d,2i-1)} and target \nolinkurl{c}, the
-reported similarity is:
-
-\[\operatorname{similarity}=1-\frac{\lVert p-c\rVert_2}{2\sqrt3}.\]
-
-The denominator is the maximum distance across the three-dimensional
-\texttt{{[}-1,1{]}} cube. Similarity is not a probability. Axis errors
-are also reported. Unknown direction makes the three-axis distance
-unavailable. Aggregate before/after comparisons use only paired valid
-assessments and report coverage and failures. Missing assessments are
-not assigned invented scores.
-
-The same small model can assess its own output, but shared weaknesses
-make independent evaluation preferable. A high similarity can coexist
-with incoherence, factual errors, or undesirable content. The
-implementation does not optimize this score during generation and does
-not include a formal semantic-fidelity metric.
-
-
-\section{Architecture, persistence, and
-privacy}\label{architecture-persistence-and-privacy}
-
-A native SwiftUI/AppKit interface communicates with a Python subprocess
-through JSON lines; no listening local web server is needed. The desktop
-app provides geometry management, document transformation, verification,
-light/dark appearance, and numeric weight editing. TXT, RTF, and DOCX
-handling preserves textual content rather than rich layout.
-
-Atomic checkpoint writes store original input, offsets, geometry,
-controls, output records, and verification. Run signatures include the
-input, settings, geometry, style, and policy version so changed settings
-do not silently resume incompatible work. Loading an older checkpoint
-validates its stored spans instead of resegmenting it. Individual
-generation or assessment failures are flagged without interrupting the
-whole document. Explicit cancellation stops the run; an in-flight API
-call can take until its timeout to return.
-
-API keys are held in memory. Local mode processes text on the computer;
-API mode sends relevant passages to the selected service. Checkpoints
-contain potentially sensitive document text and should be treated
-accordingly. The distributed package excludes personal checkpoints and
-test documents.
-
-\section{Evidence and limitations}\label{evidence-and-limitations}
-
-The release's 26 automated tests cover behaviors including checkpoint
-handling, style persistence, failure continuation, allowance accounting,
-raw-draft retention, and preservation of requested controls. Earlier
-development smoke checks established nonzero activation interventions,
-zero-strength equivalence under greedy decoding, hook cleanup, and the
-RMS budget bound. These checks establish implementation properties, not
-emotional efficacy.
-
-Exploratory development runs revealed three important failure modes:
-high intervention magnitudes can produce repetition before any full
-sentence; lower magnitudes can yield fluent but weakly emotional
-paraphrases; and segmentation changes alter which positions of a
-trajectory are sampled. A temporary whole-paragraph/reduced-steering
-recovery design improved completion on a small example but weakened the
-desired affect, and is not the current release behavior.
-
-No representative benchmark, blinded human study, multilingual
-evaluation, or statistically supported success rate is claimed.
-Controlled experiments should hold input, geometry, prompt,
-segmentation, and sampling constant while comparing unsteered and
-steered output. Report emotional distance, completion rate, repetition,
-length ratio, factual/content preservation, and human judgments
-together. Selection based on emotional distance alone can reward extreme
-or incoherent writing.
-
-\section{Conclusion}\label{conclusion}
-
-AFFECTOR makes a low-dimensional emotional trajectory operational
-through explicit transformer-state interventions and a separate
-prompt-based backend. Its value is as an inspectable experimental
-system: coordinates, editable vectors, controls, raw drafts, and
-verification are exposed. Reliable emotional transfer remains an
-empirical research problem. The current method demonstrates a
-controllable intervention mechanism but does not establish that a
-particular intervention reliably creates a specified emotional
-experience.
-
-\section{Implementation and infrastructure
-sources}\label{implementation-and-infrastructure-sources}
-
-\begin{enumerate}
-\def\labelenumi{\arabic{enumi}.}
-\item
-  Qwen team. Qwen3.5-0.8B model card and distribution.
-  \url{https://huggingface.co/Qwen/Qwen3.5-0.8B}
-\item
-  PyTorch documentation. Module forward and forward-pre hooks.
-  \url{https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html}
-\item
-  Hugging Face Transformers documentation. Text generation.
-  \url{https://huggingface.co/docs/transformers/main_classes/text_generation}
-\item
-  Apple Developer documentation. Notarizing macOS software before
-  distribution.
-  \url{https://developer.apple.com/documentation/security/notarizing-macos-software-before-distribution}
-\end{enumerate}
-
-The equations and implementation descriptions above are derived from the
-included source. Upstream documentation describes infrastructure and
-model distribution, not evidence validating AFFECTOR's
-emotional-transfer claims.
-
-\section*{AI assistance disclosure}
-This project was created with assistance from GPT-6 Astra and Codex. AI
-tools supported software development, testing, and the drafting and
-revision of this technical report. William Taggart is responsible for
-the project's research decisions and the final software and
-documentation. AI assistance does not constitute independent validation
-of the implementation or its scientific claims; the validation evidence
-and limitations are stated separately in this report.
-
-\bibliographystyle{ACM-Reference-Format}
-\bibliography{references}
-
-\section*{Suggested citation}
-William Taggart. 2026. AFFECTOR: Coordinate-Guided Text Rewriting
-through Transformer Activation Interventions. Technical report. Modern
-and Classical Languages and Literatures, Virginia Tech. November 13, 2026.
-\url{https://huggingface.co/will-taggart/AFFECTOR/blob/main/docs/TECHNICAL_PAPER.md}
-
-\end{document}

paper/{AFFECTOR-ACM-source.zip → AFFECTOR-source.zip}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14
-size 6603309
+oid sha256:1521e532082c26a297c2ca34a7e968fdb4e7bede7a8cee36a5c9207d281906c0
+size 4213592

paper/{AFFECTOR-ACM.pdf → AFFECTOR.pdf}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e059179343c7acd54f1d6b8da8ba36cdb0fe941aca291f9be6d9bf4aa5a9dd0b
-size 2131283
+oid sha256:d7b7e0a6f4b72c7977f1057accfe011d99c49c39dd70f3ce8d197a11b7efba36
+size 1954963

paper/{AFFECTOR-ACM.tex → AFFECTOR.tex}

@@ -134,7 +134,7 @@ completed benchmark. \citep{yang2026steerscope}.
 
 \begin{figure}[!htb]
 \centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-01.png}
+\includegraphics[width=.86\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-01.png}
 \caption{Document workspace with an example input, rewrite controls, and an empty output pane before generation.}
 \Description{Document workspace with an example input, rewrite controls, and an empty output pane before generation.}
 \label{fig:app-screen-1}
@@ -166,7 +166,7 @@ alignment}\label{representation-and-alignment}
 
 \begin{figure}[!htb]
 \centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-02.png}
+\includegraphics[width=.86\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-02.png}
 \caption{Geometry editor showing the selected three-point trajectory and its steering controls.}
 \Description{Geometry editor showing the selected three-point trajectory and its steering controls.}
 \label{fig:app-screen-2}
@@ -209,7 +209,7 @@ the same geometry is selected.
 
 \begin{figure}[!htb]
 \centering
-\includegraphics[width=\textwidth]{figures/illustration-01.pdf}
+\includegraphics[width=.9\textwidth]{figures/illustration-01.pdf}
 \caption{Normalized alignment schematic. Target chunks sample a continuous source path at original character midpoints; a short target can miss narrow changes in a long source trajectory.}
 \Description{One continuous path, a finite set of targets. Normalized alignment schematic. Target chunks sample a continuous source path at original character midpoints; a short target can miss narrow changes in a long source trajectory.}
 \label{fig:illustration-1}
@@ -221,7 +221,7 @@ calibration}\label{frozen-model-and-contrastive-calibration}
 
 \begin{figure}[!htb]
 \centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-03.png}
+\includegraphics[width=.86\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-03.png}
 \caption{Source-analysis dialog for generating a geometry and optionally calibrating a local activation basis.}
 \Description{Source-analysis dialog for generating a geometry and optionally calibrating a local activation basis.}
 \label{fig:app-screen-3}
@@ -274,7 +274,7 @@ computation}\label{coordinate-to-activation-computation}
 
 \begin{figure}[!htb]
 \centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-04.png}
+\includegraphics[width=.86\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-04.png}
 \caption{Expanded numerical weights for the selected geometry, including the local calibration metadata.}
 \Description{Expanded numerical weights for the selected geometry, including the local calibration metadata.}
 \label{fig:app-screen-4}
@@ -399,13 +399,7 @@ a proof of success.
 \section{Independent verification}\label{independent-verification}
 
 
-\begin{figure}[!htb]
-\centering
-\includegraphics[width=\linewidth,height=0.58\textheight,keepaspectratio]{figures/screenshot-05.png}
-\caption{Verification controls before evaluation. No verification results have been computed in this view.}
-\Description{Verification controls before evaluation. No verification results have been computed in this view.}
-\label{fig:app-screen-5}
-\end{figure}
+
 Verification assesses original and revised chunks separately with an
 unsteered evaluator or an API model. The evaluator is instructed to
 distinguish felt or conveyed emotion from mere emotion-word occurrence,

paper/ILLUSTRATIONS.json

@@ -43,17 +43,6 @@
         1590
       ],
       "caption": "Expanded numerical weights for the selected geometry, including the local calibration metadata."
-    },
-    {
-      "file": "figures/screenshot-05.png",
-      "source": "affector-05.png",
-      "crop": [
-        450,
-        270,
-        2660,
-        850
-      ],
-      "caption": "Verification controls before evaluation. No verification results have been computed in this view."
     }
   ],
   "retained_diagrams": [

paper/PAPER-SHA256SUMS.txt

@@ -1,28 +1,27 @@
-585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14  AFFECTOR-ACM-source.zip
-d78577482f74cba4163db18d88af82786c923d72cd09607bde62cb747c645c5d  AFFECTOR-ACM.bbl
-e059179343c7acd54f1d6b8da8ba36cdb0fe941aca291f9be6d9bf4aa5a9dd0b  AFFECTOR-ACM.pdf
-585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14  AFFECTOR-ACM.source.zip
-79ba8d740887aa02ed526f7f7a814feccefd2dcdf2c2765b52b3c6479ddef077  AFFECTOR-ACM.tex
-585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14  AFFECTOR-Technical-Report-ACM-source.zip
-d78577482f74cba4163db18d88af82786c923d72cd09607bde62cb747c645c5d  AFFECTOR-Technical-Report-ACM.bbl
-e059179343c7acd54f1d6b8da8ba36cdb0fe941aca291f9be6d9bf4aa5a9dd0b  AFFECTOR-Technical-Report-ACM.pdf
-585966103f53f58a9983bba63e3d27dcb2020033a2f64c6dc63684afe418ae14  AFFECTOR-Technical-Report-ACM.source.zip
-79ba8d740887aa02ed526f7f7a814feccefd2dcdf2c2765b52b3c6479ddef077  AFFECTOR-Technical-Report-ACM.tex
-e2c0590754823491af4657a764ab6682e27c5eaf0173fc9f5f03a62e84ccb308  ILLUSTRATIONS.json
+322c798131b9aadcf7ada359c42f32c22adc44ab0dbd7e066c73cbe77ecfdf55  SCREENSHOTS.json
 d14edda139a36c0bac8b56d02e5cda63ab7558c6db1424f1087189a9429bfaf0  LITERATURE_SOURCES.md
-22f8f7bf6992778eb1190ee02b6e83dacbd54ff34af7777a18b4e27a195309a3  README.md
-300e021642b37bee9bdb110a907e4387471099c5cd71ff74c0272098a3f2aa59  TECHNICAL_PAPER.md
+fb69e4bf9402090fb62cb6b32b6b589d6412158204f3099b6eb754f87b1ffad2  AFFECTOR.tex
+9257f38423bd7e496f1a0916c0fbaefbfb32ab544a684ca9a411508201f0535e  references.bib
+3079f84469ca2b0c85e3aa7a01add2a78ec6640c7226a3166209d2495a5c3912  source.md
+3079f84469ca2b0c85e3aa7a01add2a78ec6640c7226a3166209d2495a5c3912  TECHNICAL_PAPER.md
+d7b7e0a6f4b72c7977f1057accfe011d99c49c39dd70f3ce8d197a11b7efba36  AFFECTOR.pdf
+d78577482f74cba4163db18d88af82786c923d72cd09607bde62cb747c645c5d  AFFECTOR.bbl
+eed8b979a5a299b42e925d9027332e7df876400dcef046f2cfe26beef91d1189  render_figures.py
+7f1c5ae6a0a8d61880debe26cc0b0a91ac74dd51841495920ae0cdd7ed23f83f  README.md
 4bd1a1b7f6af31b12b9c92bcd978fe116482892b3463f8ec9c922bc1f636c7a0  figure-specifications.json
+62971a4d98692c4bead7f7771e4fa818929ba8700ead9dd80859c355ad4c2242  ILLUSTRATIONS.json
 b11798a28d94d60110a7b19f58107d5e60926b68265f64e62f59e9230a8f500d  figures/illustration-01.pdf
-d2ae42a17ff3f16b89a7cb85d21ac1f3c7a19c2bc62d61f1cc581c2ca6d3e596  figures/illustration-01.png
-d0b507ac78fbfaa992c17a575e9af1116261207de889edc413c4aee62abd925f  figures/illustration-02.pdf
+af32b230516b71d5534df205ea2fae6230574640f50c5aacbfc5c9aba38f62ed  figures/illustration-03.png
 9a672688e6520fb9924c00d252d1a2f2a3da7af373a64131bca30240718cd980  figures/illustration-02.png
+d0b507ac78fbfaa992c17a575e9af1116261207de889edc413c4aee62abd925f  figures/illustration-02.pdf
+d2ae42a17ff3f16b89a7cb85d21ac1f3c7a19c2bc62d61f1cc581c2ca6d3e596  figures/illustration-01.png
 8c5f89f3ff786ae61705eabf33640b0574daa74dab66198a39ec0f36b9d65d2b  figures/illustration-03.pdf
-af32b230516b71d5534df205ea2fae6230574640f50c5aacbfc5c9aba38f62ed  figures/illustration-03.png
-65f19c88a198940e931b8ada7ce61221e8b04c66bef040f62bf9b7c39f759a7f  figures/illustration-04.pdf
+7d8f30b829993326e8d764ae18b3974acddbd86b760d4071bdff4edfcb9b299a  figures/illustration-05.png
 484091e71f12c3f19505ffe96e440c6317c2aecacde8634fe560bf13a3485336  figures/illustration-04.png
+65f19c88a198940e931b8ada7ce61221e8b04c66bef040f62bf9b7c39f759a7f  figures/illustration-04.pdf
 a6a497a38f4ba9de8088f410535bee13dd862d1a97f4175d205df768e1d2c1c9  figures/illustration-05.pdf
-7d8f30b829993326e8d764ae18b3974acddbd86b760d4071bdff4edfcb9b299a  figures/illustration-05.png
-9257f38423bd7e496f1a0916c0fbaefbfb32ab544a684ca9a411508201f0535e  references.bib
-eed8b979a5a299b42e925d9027332e7df876400dcef046f2cfe26beef91d1189  render_figures.py
-300e021642b37bee9bdb110a907e4387471099c5cd71ff74c0272098a3f2aa59  source.md
+182c73f6f6a527ce52a3a3bec0470af684ac8c67dc787ccacf44ef98a2ddc353  figures/screenshot-04.png
+8d267fd6d50e2146279f1f33e07f88a3cbf76d023dd9ee36b29e390ac0473cd1  figures/screenshot-02.png
+759dabd81a2ce67f01a3ec96a01b014468402baee5774792fccd5b7fe53af80a  figures/screenshot-03.png
+ff1ace53310f4f8ea57dedb7a202edd7404886091ed34b1bcc70cbb6c93b2779  figures/screenshot-01.png
+1521e532082c26a297c2ca34a7e968fdb4e7bede7a8cee36a5c9207d281906c0  AFFECTOR-source.zip

paper/README.md

@@ -1,7 +1,7 @@
 # AFFECTOR illustrated technical report
 
-**Technical paper:** [PDF](AFFECTOR-ACM.pdf) · [LaTeX](AFFECTOR-ACM.tex) · [Markdown](TECHNICAL_PAPER.md) · [Illustrations](figures/)
+**Technical paper:** [PDF](AFFECTOR.pdf) · [LaTeX](AFFECTOR.tex) · [Markdown](TECHNICAL_PAPER.md) · [Illustrations](figures/)
 
-Build with `tectonic AFFECTOR-ACM.tex` (rename the resulting PDF to `AFFECTOR-ACM.pdf` where needed). The source archive includes all figure PDFs and PNGs.
+Build with `tectonic AFFECTOR.tex` (rename the resulting PDF to `AFFECTOR.pdf` where needed). The source archive includes all figure PDFs and PNGs.
 
 Regenerate the diagrams with `python3 render_figures.py` (requires Matplotlib). Diagram titles and captions are recorded in `ILLUSTRATIONS.json`; vector PDF and raster PNG versions are provided.

paper/SCREENSHOTS.json

@@ -42,16 +42,5 @@
       1590
     ],
     "caption": "Expanded numerical weights for the selected geometry, including the local calibration metadata."
-  },
-  {
-    "file": "figures/screenshot-05.png",
-    "source": "affector-05.png",
-    "crop": [
-      450,
-      270,
-      2660,
-      850
-    ],
-    "caption": "Verification controls before evaluation. No verification results have been computed in this view."
   }
 ]

paper/TECHNICAL_PAPER.md

@@ -1,6 +1,6 @@
 # AFFECTOR: Coordinate-Guided Text Rewriting through Transformer Activation Interventions
 
-**Technical paper:** [PDF](AFFECTOR-ACM.pdf) · [LaTeX source](AFFECTOR-ACM.tex) · [Complete source ZIP](AFFECTOR-ACM-source.zip)
+**Technical paper:** [PDF](AFFECTOR.pdf) · [LaTeX source](AFFECTOR.tex) · [Complete source ZIP](AFFECTOR-source.zip)
 
 **William Taggart**  
 Modern and Classical Languages and Literatures, Virginia Tech  
@@ -141,9 +141,7 @@ These mechanisms trade completeness for bounded readable output. Sentence punctu
 
 Verification assesses original and revised chunks separately with an unsteered evaluator or an API model. The evaluator is instructed to distinguish felt or conveyed emotion from mere emotion-word occurrence, identify experiencers and emotional targets, and supply exact quoted evidence. It returns valence, direction, intensity, emotional labels, uncertainty, and concise explanations. Scores are interpretive estimates, not psychometric measurements.
 
-![Verification controls before evaluation. No verification results have been computed in this view.](figures/screenshot-05.png)
 
-*Verification controls before evaluation. No verification results have been computed in this view.*
 For assessed coordinate `p=(v,d,2i-1)` and target `c`, the reported similarity is:
 
 `similarity = 1 - ||p-c||_2 / (2 sqrt(3))`.

paper/source.md

@@ -1,6 +1,6 @@
 # AFFECTOR: Coordinate-Guided Text Rewriting through Transformer Activation Interventions
 
-**Technical paper:** [PDF](AFFECTOR-ACM.pdf) · [LaTeX source](AFFECTOR-ACM.tex) · [Complete source ZIP](AFFECTOR-ACM-source.zip)
+**Technical paper:** [PDF](AFFECTOR.pdf) · [LaTeX source](AFFECTOR.tex) · [Complete source ZIP](AFFECTOR-source.zip)
 
 **William Taggart**  
 Modern and Classical Languages and Literatures, Virginia Tech  
@@ -141,9 +141,7 @@ These mechanisms trade completeness for bounded readable output. Sentence punctu
 
 Verification assesses original and revised chunks separately with an unsteered evaluator or an API model. The evaluator is instructed to distinguish felt or conveyed emotion from mere emotion-word occurrence, identify experiencers and emotional targets, and supply exact quoted evidence. It returns valence, direction, intensity, emotional labels, uncertainty, and concise explanations. Scores are interpretive estimates, not psychometric measurements.
 
-![Verification controls before evaluation. No verification results have been computed in this view.](figures/screenshot-05.png)
 
-*Verification controls before evaluation. No verification results have been computed in this view.*
 For assessed coordinate `p=(v,d,2i-1)` and target `c`, the reported similarity is:
 
 `similarity = 1 - ||p-c||_2 / (2 sqrt(3))`.