paper
Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
paperactiveprovisional
where-do-models-find-happiness-emotion-vectors-in-open-source-llms-74cf7330·1 events·first seen 2d agoAliases: Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
Co-occurring entities
More like this (12)
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMsMeasuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder TransferMultimodal Large Language ModelsLanguage Modeling LossModeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language ModelsAgentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and ApplicationApparent Psychological Profiles of Large Language Models are Largely a Measurement ArtifactLatent Context Language ModelsWatch, Remember, Reason: Human-View Video Understanding with MLLMsStylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMsUnified Multimodal Models (UMMs)Gaze Heads: How VLMs Look at What They Describe
Recent events (1)
Emotion vectors replicated in open-weight LLMs with architecture-dependent valence geometry
A new arXiv preprint extends prior findings on emotion vectors in Claude Sonnet 4.5 to two open-weight models, Apertus-8B-Instruct-2509 and Gemma-4-E4B-it, by extracting emotion contrast vectors across all layers. The authors recover valence geometry in both models (peak PC1-valence correlations of r=0.76 and r=0.83, near Claude's r=0.81) but find notable architectural differences: Gemma encodes valence strongly in early layers while Apertus shows the opposite pattern. Arousal encoding proves sensitive to the corpus used for extraction, suggesting uneven distribution of arousal-relevant cues across model-generated text.