✳flâneur — a map of the web's best reading

[2606.26987] Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs

arxiv.org · 691 words · saved by 1 readers

Abstract:Recent work identified emotion vectors in Claude Sonnet 4.5, which are internal representations that encode emotion concepts, causally influence behavior, and exhibit geometry mirroring human psychological structure. We test the generality of these findings in two open-weight models, Apertus-8B-Instruct-2509 and Gemma-4-E4B-it, extracting emotion contrast vectors across all layers, using two model-generated corpora. We recover valence geometry for both models, with peak PC1--valence correlations of $r = 0.76$ and $r = 0.83$, approaching the $r = 0.81$ reported for this http URL replication, we observe notable differences in how valence representations emerge across model depth. In Gemma-4-E4B-it, valence is strongly encoded in early layers but collapses towards later layers, whereas Apertus-8B-Instruct-2509 exhibits the opposite pattern, with valence representations absent in early layers, but emerging at mid depths. Arousal encoding, in contrast, is sensitive to the extraction corpus: both models show stronger PC2--arousal alignment with Gemma-generated stories ($r$ up to $0.45$) than Apertus-generated ones ($r \leq 0.21$), suggesting arousal-relevant cues are unevenly distributed across generated corpora. We open-source our experiment code and dataset for reproducible investigation of emotion representations across language model architectures.

[2606.26987] Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2606.26987 (cs) [Submitted on 25 Jun 2026] Title: Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs Authors: Sinie van der Ben , Raphaël Baur , Yannick Metz , Mennatallah El-Assady View a PDF of the paper titled Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs, by Sinie van der Ben and Ra

Explore this link on the map →

related reading