Move technical report bundle to paper directory

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 source/artifacts/AFFECTOR.icns filter=lfs diff=lfs merge=lfs -text
 docs/acm/AFFECTOR-ACM.pdf filter=lfs diff=lfs merge=lfs -text
 docs/AFFECTOR-Technical-Paper.pdf filter=lfs diff=lfs merge=lfs -text
+paper/AFFECTOR-ACM.pdf filter=lfs diff=lfs merge=lfs -text

paper/AFFECTOR-ACM-source.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f33fe01d0739c2691119bb0af974528fd6cec1676268ddef0cf9d0d56ae252
+size 177311

paper/AFFECTOR-ACM.bbl

@@ -0,0 +1,264 @@
+%%% -*-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-ACM.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb0ee2fa99910e7eb78788638283a7a07c0f8dfc115a41b71980eabf2d49385
+size 105752

paper/AFFECTOR-ACM.tex

@@ -0,0 +1,476 @@
+% ACM manuscript 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}
+\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}
+
+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}
+
+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.
+
+\section{Frozen model and contrastive
+calibration}\label{frozen-model-and-contrastive-calibration}
+
+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}
+
+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}
+
+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. ACM manuscript
+edition, November 13, 2026.
+\url{https://huggingface.co/will-taggart/AFFECTOR/blob/main/docs/TECHNICAL_PAPER.md}
+
+
+\end{document}

paper/LITERATURE_SOURCES.md

@@ -0,0 +1,100 @@
+# Literature source verification
+
+Checked November 13, 2026. This is a focused literature selection, not an exhaustive systematic review or independent replication. Bibliographic metadata was checked on arXiv abstract records and compared with the associated HTML/PDF text. The section locations below identify support for the bounded summaries in the reports. Peer-review status is not inferred from arXiv hosting.
+
+## R1. Activation Addition: Steering Language Models Without Optimization
+
+Authors: Alex Turner; Lisa Thiergart; David Udell; Gavin Leech; Ulisse Mini; Monte MacDiarmid.
+
+Record: [2308.10248v1](https://arxiv.org/abs/2308.10248v1). Paper: [version-specific text](https://arxiv.org/html/2308.10248v1). Version date: 2023-08-20.
+
+Verification notes: Methods; natural-language control of sentiment, topic, style.
+
+## R2. Steering Llama 2 via Contrastive Activation Addition
+
+Authors: Nina Panickssery; Nick Gabrieli; Julian Schulz; Meg Tong; Evan Hubinger; Alexander Matt Turner.
+
+Record: [2312.06681v4](https://arxiv.org/abs/2312.06681v4). Paper: [version-specific text](https://arxiv.org/html/2312.06681v4). Version date: 2024-07-05.
+
+Verification notes: Section 3 and Figure 1; sections 4-7; first submitted 2023.
+
+## R3. AI shares emotion with humans across languages and cultures
+
+Authors: Xiuwen Wu; Hao Wang; Zhiang Yan; Xiaohan Tang; Pengfei Xu; Wai-Ting Siok; Ping Li; Jia-Hong Gao; Bingjiang Lyu; Lang Qin.
+
+Record: [2506.13978v1](https://arxiv.org/abs/2506.13978v1). Paper: [version-specific text](https://arxiv.org/pdf/2506.13978v1). Version date: 2025-06-11.
+
+Verification notes: PDF abstract and introduction; emotion-space alignment and steering; no arXiv HTML.
+
+## R4. The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation
+
+Authors: Diaoulé Diallo; Katharina Dworatzyk; Sophie Jentzsch; Peer Schütt; Sabine Theis; Tobias Hecking.
+
+Record: [2601.21505v1](https://arxiv.org/abs/2601.21505v1). Paper: [version-specific text](https://arxiv.org/html/2601.21505v1). Version date: 2026-01-29.
+
+Verification notes: Sections V-VII; arXiv record also lists IEEE Access 13 (2025), 191443-191457, DOI 10.1109/ACCESS.2025.3628500.
+
+## R5. How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study
+
+Authors: Moran Sun; Tianlin Li; Yuwei Zheng; Zhenhong Zhou; Aishan Liu; Xianglong Liu; Yang Liu.
+
+Record: [2604.00005v1](https://arxiv.org/abs/2604.00005v1). Paper: [version-specific text](https://arxiv.org/html/2604.00005v1). Version date: 2026-03-09.
+
+Verification notes: Sections 3-5; VAD-based E-STEER; date follows submission history rather than ID prefix.
+
+## R6. Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison
+
+Authors: Jihoon Jeong.
+
+Record: [2604.04064v1](https://arxiv.org/abs/2604.04064v1). Paper: [version-specific text](https://arxiv.org/html/2604.04064v1). Version date: 2026-04-05.
+
+Verification notes: Sections 3 and 5-8; exploratory model-dependent regimes; no independent replication claimed.
+
+## R7. Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders
+
+Authors: Bangzhao Shu; Arinjay Singh; Mai ElSherief.
+
+Record: [2604.25866v3](https://arxiv.org/abs/2604.25866v3). Paper: [version-specific text](https://arxiv.org/html/2604.25866v3). Version date: 2026-10-24.
+
+Verification notes: Sections 4-6; current v3 title differs from v1 From Syntax to Emotion.
+
+## R8. Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models
+
+Authors: Yibo Wang; Jisheng Dang; Bimei Wang; Yitao Wu; Wencan Zhang; Hong Peng; Jizhao Liu; Bin Hu; Qi Tian; Tat-Seng Chua.
+
+Record: [2609.22135v1](https://arxiv.org/abs/2609.22135v1). Paper: [version-specific text](https://arxiv.org/html/2609.22135v1). Version date: 2026-08-24.
+
+Verification notes: Sections III-V and VIII; date follows submission history rather than ID prefix.
+
+## R9. Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs
+
+Authors: JuHeon Ha; Byounghan Lee; Yunseo Choi; Kyung-Ah Sohn.
+
+Record: [2609.15654v1](https://arxiv.org/abs/2609.15654v1). Paper: [version-specific text](https://arxiv.org/html/2609.15654v1). Version date: 2026-09-14.
+
+Verification notes: Sections 3-4 and 7; EPITOME proxy outcomes; arXiv comments report acceptance to EMNLP 2026 main conference.
+
+## R10. Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models
+
+Authors: Sasha Cui; Zhongren Chen.
+
+Record: [2509.22739v3](https://arxiv.org/abs/2509.22739v3). Paper: [version-specific text](https://arxiv.org/html/2509.22739v3). Version date: 2026-05-15.
+
+Verification notes: Sections 2-3 and 5; first submitted 2025; v3 checked.
+
+## R11. Dynamically Scaled Activation Steering
+
+Authors: Alex Ferrando; Xavier Suau; Jordi Gonzàlez; Pau Rodriguez.
+
+Record: [2512.03661v2](https://arxiv.org/abs/2512.03661v2). Paper: [version-specific text](https://arxiv.org/html/2512.03661v2). Version date: 2026-07-30.
+
+Verification notes: Sections 3-5; first submitted 2025; v2 checked; author names follow arXiv metadata.
+
+## R12. Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods
+
+Authors: Haotian Yang; Huikang Jiang; Yucheng Wu; Wen-Jie Jiang; Chenpeng Wang; Yibin Lou; Liangming Pan.
+
+Record: [2610.07722v1](https://arxiv.org/abs/2610.07722v1). Paper: [version-specific text](https://arxiv.org/html/2610.07722v1). Version date: 2026-10-06.
+
+Verification notes: Sections 3-5; efficacy and side effects under matched evaluation.
+

paper/README.md

@@ -0,0 +1,21 @@
+# AFFECTOR: Coordinate-Guided Text Rewriting through Transformer Activation Interventions
+
+Uses the official ACM acmart class with manuscript, screen, and nonacm options. This is an independently distributed report, not an assertion of ACM publication or acceptance. No venue, DOI, or copyright transfer is invented.
+
+## Build
+
+With a current TeX Live/MacTeX installation including acmart:
+
+    latexmk -pdf AFFECTOR-ACM.tex
+
+Or Tectonic 0.17.0:
+
+    tectonic --keep-logs --keep-intermediates AFFECTOR-ACM.tex
+
+The bibliography uses ACM-Reference-Format.bst. The generated .bbl is included; references.bib remains editable. All packages are standard TeX distribution packages. No shell escape is needed. The manuscript layout is single-column; change manuscript to sigconf for a venue requiring two columns, then recheck layout.
+
+Includes the source Markdown snapshot and citation verification notes. Equations, tables, and citations are native LaTeX. AI disclosure appears immediately before the references.
+
+Original report: https://huggingface.co/will-taggart/AFFECTOR/blob/main/docs/TECHNICAL_PAPER.md
+
+Build verified with Tectonic 0.17.0 and bundled acmart v1.83 (2022/02/19). All 12 bibliography entries resolve.

paper/references.bib

@@ -0,0 +1,120 @@
+@misc{turner2023actadd,
+  author = {Alex Turner and Lisa Thiergart and David Udell and Gavin Leech and Ulisse Mini and Monte MacDiarmid},
+  title = {{Activation Addition: Steering Language Models Without Optimization}},
+  year = {2023},
+  eprint = {2308.10248v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2308.10248v1},
+  note = {Cited version dated 2023-08-20; metadata checked 2026-11-13}
+}
+
+@misc{panickssery2024caa,
+  author = {Nina Panickssery and Nick Gabrieli and Julian Schulz and Meg Tong and Evan Hubinger and Alexander Matt Turner},
+  title = {{Steering Llama 2 via Contrastive Activation Addition}},
+  year = {2024},
+  eprint = {2312.06681v4},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2312.06681v4},
+  note = {Cited version dated 2024-07-05; metadata checked 2026-11-13}
+}
+
+@misc{wu2025emotion,
+  author = {Xiuwen Wu and Hao Wang and Zhiang Yan and Xiaohan Tang and Pengfei Xu and Wai-Ting Siok and Ping Li and Jia-Hong Gao and Bingjiang Lyu and Lang Qin},
+  title = {{AI shares emotion with humans across languages and cultures}},
+  year = {2025},
+  eprint = {2506.13978v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2506.13978v1},
+  note = {Cited version dated 2025-06-11; metadata checked 2026-11-13}
+}
+
+@misc{diallo2026style,
+  author = {Diaoulé Diallo and Katharina Dworatzyk and Sophie Jentzsch and Peer Schütt and Sabine Theis and Tobias Hecking},
+  title = {{The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation}},
+  year = {2026},
+  eprint = {2601.21505v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2601.21505v1},
+  note = {Cited version dated 2026-01-29; metadata checked 2026-11-13}
+}
+
+@misc{sun2026emotion,
+  author = {Moran Sun and Tianlin Li and Yuwei Zheng and Zhenhong Zhou and Aishan Liu and Xianglong Liu and Yang Liu},
+  title = {{How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study}},
+  year = {2026},
+  eprint = {2604.00005v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2604.00005v1},
+  note = {Cited version dated 2026-03-09; metadata checked 2026-11-13}
+}
+
+@misc{jeong2026emotion,
+  author = {Jihoon Jeong},
+  title = {{Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison}},
+  year = {2026},
+  eprint = {2604.04064v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2604.04064v1},
+  note = {Cited version dated 2026-04-05; metadata checked 2026-11-13}
+}
+
+@misc{shu2026emotion,
+  author = {Bangzhao Shu and Arinjay Singh and Mai ElSherief},
+  title = {{Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders}},
+  year = {2026},
+  eprint = {2604.25866v3},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2604.25866v3},
+  note = {Cited version dated 2026-10-24; metadata checked 2026-11-13}
+}
+
+@misc{wang2026readbest,
+  author = {Yibo Wang and Jisheng Dang and Bimei Wang and Yitao Wu and Wencan Zhang and Hong Peng and Jizhao Liu and Bin Hu and Qi Tian and Tat-Seng Chua},
+  title = {{Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models}},
+  year = {2026},
+  eprint = {2609.22135v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2609.22135v1},
+  note = {Cited version dated 2026-08-24; metadata checked 2026-11-13}
+}
+
+@misc{ha2026empathy,
+  author = {JuHeon Ha and Byounghan Lee and Yunseo Choi and Kyung-Ah Sohn},
+  title = {{Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs}},
+  year = {2026},
+  eprint = {2609.15654v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2609.15654v1},
+  note = {Cited version dated 2026-09-14; metadata checked 2026-11-13}
+}
+
+@misc{cui2025pas,
+  author = {Sasha Cui and Zhongren Chen},
+  title = {{Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models}},
+  year = {2025},
+  eprint = {2509.22739v3},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2509.22739v3},
+  note = {Cited version dated 2026-05-15; metadata checked 2026-11-13}
+}
+
+@misc{ferrando2025dsas,
+  author = {Alex Ferrando and Xavier Suau and Jordi Gonzàlez and Pau Rodriguez},
+  title = {{Dynamically Scaled Activation Steering}},
+  year = {2025},
+  eprint = {2512.03661v2},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2512.03661v2},
+  note = {Cited version dated 2026-07-30; metadata checked 2026-11-13}
+}
+
+@misc{yang2026steerscope,
+  author = {Haotian Yang and Huikang Jiang and Yucheng Wu and Wen-Jie Jiang and Chenpeng Wang and Yibin Lou and Liangming Pan},
+  title = {{Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods}},
+  year = {2026},
+  eprint = {2610.07722v1},
+  archivePrefix = {arXiv},
+  url = {https://arxiv.org/abs/2610.07722v1},
+  note = {Cited version dated 2026-10-06; metadata checked 2026-11-13}
+}
+

paper/source.md

@@ -0,0 +1,197 @@
+# AFFECTOR: Coordinate-Guided Text Rewriting through Transformer Activation Interventions
+
+**William Taggart**  
+Modern and Classical Languages and Literatures, Virginia Tech  
+Email: wtaggart@vt.edu  
+November 13, 2026 · Implementation report · Desktop version 0.1.0
+
+## 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.
+
+## 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.
+
+**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. [Turner et al., 2023 (R1)](https://arxiv.org/abs/2308.10248v1); [Panickssery et al., 2024 (R2)](https://arxiv.org/abs/2312.06681v4).
+
+**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. [Wu et al., 2025 (R3)](https://arxiv.org/abs/2506.13978v1); [Diallo et al., 2026 arXiv version (R4)](https://arxiv.org/abs/2601.21505v1).
+
+**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. [Sun et al., 2026 (R5)](https://arxiv.org/abs/2604.00005v1); [Jeong, 2026 (R6)](https://arxiv.org/abs/2604.04064v1).
+
+**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. [Shu et al., 2026, v3 (R7)](https://arxiv.org/abs/2604.25866v3); [Wang et al., 2026 (R8)](https://arxiv.org/abs/2609.22135v1).
+
+**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. [Ha et al., 2026 (R9)](https://arxiv.org/abs/2609.15654v1); [Cui and Chen, 2025, revised 2026 (R10)](https://arxiv.org/abs/2509.22739v3); [Ferrando et al., 2025, revised 2026 (R11)](https://arxiv.org/abs/2512.03661v2).
+
+**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. [Yang et al., 2026 (R12)](https://arxiv.org/abs/2610.07722v1).
+
+## 1. Problem formulation
+
+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.
+
+## 2. Representation and alignment
+
+A geometry consists of ordered points `(t, v, d, i)`. Position `t` is in `[0,1]`; valence `v` and direction `d` are in `[-1,1]`; intensity `i` is in `[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 `a` through `b` in an input of length `N`, its target position is `(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.
+
+## 3. Frozen model and contrastive calibration
+
+The local backend loads Qwen3.5-0.8B at revision `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 `l` and axis `j`, the mean contrast is:
+
+`u[l,j] = (1/4) sum_k (h_plus[l,j,k] - h_minus[l,j,k])`.
+
+With `RMS(x) = sqrt(mean_r(x[r]^2))`, normalization gives:
+
+`B[l,j] = u[l,j] / max(RMS(u[l,j]), 1e-8)`.
+
+The resulting `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.
+
+## 4. Coordinate-to-activation computation
+
+Axis temperature `T` transforms each coordinate magnitude while retaining its sign:
+
+`q[j] = sign(c[j]) * abs(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 `h`, strength `s`, and layer weight `w[l]`, the proposed perturbation is:
+
+`delta_raw = (q @ B[l]) * RMS(h) * s * w[l]`.
+
+Inertia `rho` combines this proposal with the previous applied perturbation within the same chunk:
+
+`delta_mix = rho * delta_previous + (1-rho) * delta_raw`.
+
+The first step uses the raw proposal directly. A relative RMS budget `beta` then bounds the perturbation:
+
+`delta = delta_mix * min(1, beta * RMS(h) / max(RMS(delta_mix), 1e-12))`.
+
+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.
+
+## 5. Intervention within the transformer
+
+Let `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 + FFN(Norm(h))`.
+
+AFFECTOR implements:
+
+`y = (h + delta) + FFN(Norm(h + delta))`.
+
+A pre-hook on the feed-forward normalization adds `delta` to its input, and a post-hook on the block output adds the same `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.
+
+## 6. 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.
+
+## 7. Independent verification
+
+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 `p=(v,d,2i-1)` and target `c`, the reported similarity is:
+
+`similarity = 1 - ||p-c||_2 / (2 sqrt(3))`.
+
+The denominator is the maximum distance across the three-dimensional `[-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.
+
+## 8. 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.
+
+## 9. 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.
+
+## 10. 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.
+
+## 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.
+
+## References
+
+1. Qwen team. Qwen3.5-0.8B model card and distribution. https://huggingface.co/Qwen/Qwen3.5-0.8B
+
+2. PyTorch documentation. Module forward and forward-pre hooks. https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html
+
+3. Hugging Face Transformers documentation. Text generation. https://huggingface.co/docs/transformers/main_classes/text_generation
+
+4. Apple Developer documentation. Notarizing macOS software before distribution. https://developer.apple.com/documentation/security/notarizing-macos-software-before-distribution
+
+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.
+
+## Research references
+
+Version-specific arXiv records are linked below. Years distinguish original release from later revision where applicable. These research references supplement the implementation and infrastructure sources elsewhere in this report. Reusable citations: [BibTeX](references.bib). Verification details: [source-check notes](LITERATURE_SOURCES.md).
+
+**R1.** Alex Turner; Lisa Thiergart; David Udell; Gavin Leech; Ulisse Mini; Monte MacDiarmid. 2023. Activation Addition: Steering Language Models Without Optimization. [arXiv:2308.10248v1](https://arxiv.org/abs/2308.10248v1). Cited version dated 2023-08-20.
+
+**R2.** Nina Panickssery; Nick Gabrieli; Julian Schulz; Meg Tong; Evan Hubinger; Alexander Matt Turner. 2024. Steering Llama 2 via Contrastive Activation Addition. [arXiv:2312.06681v4](https://arxiv.org/abs/2312.06681v4). Cited version dated 2024-07-05.
+
+**R3.** Xiuwen Wu; Hao Wang; Zhiang Yan; Xiaohan Tang; Pengfei Xu; Wai-Ting Siok; Ping Li; Jia-Hong Gao; Bingjiang Lyu; Lang Qin. 2025. AI shares emotion with humans across languages and cultures. [arXiv:2506.13978v1](https://arxiv.org/abs/2506.13978v1). Cited version dated 2025-06-11.
+
+**R4.** Diaoulé Diallo; Katharina Dworatzyk; Sophie Jentzsch; Peer Schütt; Sabine Theis; Tobias Hecking. 2026. The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation. [arXiv:2601.21505v1](https://arxiv.org/abs/2601.21505v1). Cited version dated 2026-01-29. ArXiv record lists IEEE Access 13 (2025), 191443-191457; DOI: 10.1109/ACCESS.2025.3628500.
+
+**R5.** Moran Sun; Tianlin Li; Yuwei Zheng; Zhenhong Zhou; Aishan Liu; Xianglong Liu; Yang Liu. 2026. How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study. [arXiv:2604.00005v1](https://arxiv.org/abs/2604.00005v1). Cited version dated 2026-03-09.
+
+**R6.** Jihoon Jeong. 2026. Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison. [arXiv:2604.04064v1](https://arxiv.org/abs/2604.04064v1). Cited version dated 2026-04-05.
+
+**R7.** Bangzhao Shu; Arinjay Singh; Mai ElSherief. 2026. Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders. [arXiv:2604.25866v3](https://arxiv.org/abs/2604.25866v3). Cited version dated 2026-10-24.
+
+**R8.** Yibo Wang; Jisheng Dang; Bimei Wang; Yitao Wu; Wencan Zhang; Hong Peng; Jizhao Liu; Bin Hu; Qi Tian; Tat-Seng Chua. 2026. Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models. [arXiv:2609.22135v1](https://arxiv.org/abs/2609.22135v1). Cited version dated 2026-08-24.
+
+**R9.** JuHeon Ha; Byounghan Lee; Yunseo Choi; Kyung-Ah Sohn. 2026. Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs. [arXiv:2609.15654v1](https://arxiv.org/abs/2609.15654v1). Cited version dated 2026-09-14. ArXiv comments report acceptance to the EMNLP 2026 main conference.
+
+**R10.** Sasha Cui; Zhongren Chen. 2025. Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models. [arXiv:2509.22739v3](https://arxiv.org/abs/2509.22739v3). Cited version dated 2026-05-15.
+
+**R11.** Alex Ferrando; Xavier Suau; Jordi Gonzàlez; Pau Rodriguez. 2025. Dynamically Scaled Activation Steering. [arXiv:2512.03661v2](https://arxiv.org/abs/2512.03661v2). Cited version dated 2026-07-30.
+
+**R12.** Haotian Yang; Huikang Jiang; Yucheng Wu; Wen-Jie Jiang; Chenpeng Wang; Yibin Lou; Liangming Pan. 2026. Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods. [arXiv:2610.07722v1](https://arxiv.org/abs/2610.07722v1). Cited version dated 2026-10-06.
+