arXiv AI
Jun 26
Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
arXiv:2606. 26987v1 Announce Type: cross Abstract: Recent work identified emotion vectors in Claude Sonnet 4.
Do Large Language Models Have Emotions?
arXiv:2606. 14742v1 Announce Type: cross Abstract: Do LLMs have emotions?
Related stories
arXiv AI
Jul 22
Semantic Primes as Explanans for Emotion in Large Language Models
arXiv:2607. 18691v1 Announce Type: new Abstract: Progresses have been made on understanding emotion mechanisms of large language models (LLMs).
arXiv Machine Learning
Sep 22
Replicating the Geometry of Emotion Representations in a Base Open-Weights Model
Sofroniew et al. (2026) showed that emotion concepts in Claude Sonnet 4.5 are encoded as vectors whose geometry mirrors human affect psychology. This study replicates that finding using the base pretrained model google/gemma-2-27b, generating 205,200 Claude Sonnet 4.5 stories, extracting 171 emotion vectors, and recovering a similar affective circumplex with principal components explaining comparable variance. The analysis further identifies a sharp geometric seam at layers 22‑26, demonstrates that much of the geometry already exists in static token embeddings, and shows that the geometry predicts token‑level co‑activation with high correlation.
arXiv Computation and Language
Sep 22
Functional Emotion Without Character: Large Language Models, Aristotelian Disposition, and the Limits of Behavioral Alignment
arXiv:2609.22362v1 Announce Type: new Abstract: Debates about whether artificial systems can feel are often forced between two unsatisfactory positions: behavioral equivalence is treated as sufficien...
arXiv AI
Aug 13
TEMPER: Testing Emotional Perturbation in Quantitative Reasoning
arXiv:2604. 07801v2 Announce Type: replace-cross Abstract: Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language.
arXiv Computation and Language
Aug 27
Controllable Affective Generation via Latent Vector Steering
The paper introduces EmoVec, a lightweight framework that enables controllable affective generation in large language models by steering latent vectors. EmoVec identifies emotion-specific directions from paired neutral and emotion-conditioned responses using contrastive activation addition, then refines these directions through task-specific debiasing and principal subspace removal. During inference, the refined vectors are injected into the final residual stream with static or scenario-adaptive scaling, allowing continuous control over emotional intensity without updating model weights, and experiments across three LLMs and eight emotions demonstrate improved emotional salience while preserving semantic content, fluency, and coherence.
arXiv AI
Jun 12
Emergence of Hierarchical Emotion Organization in Large Language Models
arXiv:2507. 10599v2 Announce Type: replace-cross Abstract: As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for ethical deployment.
arXiv Machine Learning
Jun 9
Decoding Naturalistic Emotion Dynamics from the Brain: An LLM-Enhanced Regression Framework
arXiv:2606. 07707v1 Announce Type: new Abstract: Decoding emotional states from neural signals has been typically framed as a discrete, single-label classification task based on emotionally stable stimuli, a formulation that oversimplifies the continuous, fluid, and co-occurring nature of human affect.
arXiv AI
Jul 15
Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?
arXiv:2607. 12631v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains, understanding contextual factors that may modulate their decision-making becomes critical.
arXiv AI
Sep 16
The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It
arXiv:2609.16247v1 Announce Type: new Abstract: Large language models sometimes behave in ways resembling human emotional responses, and recent work has identified internal representations that may e...
arXiv AI
Sep 10
A Computational Implementation of a Goal-Directed Theory of Affect
arXiv:2609.06654v1 Announce Type: new Abstract: Computational modeling of emotion has long faced a tension between descriptive, "snapshot-based" appraisal models and granular, signal-driven architect...
arXiv AI
Sep 1
Do Large Language Models Possess a Theory of Mind? A Comparative Evaluation Using the Strange Stories Paradigm
arXiv:2603.18007v2 Announce Type: replace-cross Abstract: The study explores whether current Large Language Models (LLMs) exhibit Theory of Mind (ToM) capabilities -- specifically, the ability to inf...