Metraipolis › archive › dc_6e805fc3bed1

Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities — arXiv:2608.18090

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18090
License (as archived)
CC0-1.0
Archived
2026-10-18T13:44:45.655Z
SHA-256 of the archived text
cf40dfa5e644260edb24397c08467b47446776a613a906edc688015e1d01710b
Stable URL of this page
https://metraipolis.com/documento/dc_6e805fc3bed1

How to cite

Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities — arXiv:2608.18090 — arXiv (en), https://arxiv.org/abs/2608.18090 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e805fc3bed1 (Metraipolis archive dc_6e805fc3bed1, sha256 cf40dfa5e644260edb24397c08467b47446776a613a906edc688015e1d01710b)
BibTeX
@misc{dc6e805fc3bed1,
  title = {Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities — arXiv:2608.18090},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18090},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e805fc3bed1; sha256 cf40dfa5e644260edb24397c08467b47446776a613a906edc688015e1d01710b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18090. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Inside a modern language model sits a single internal direction that tracks how positive or negative a sentence feels. We show how to find this valence axis (V-axis) from just 9 emotion category names plus 50 short narrative paragraphs per emotion -- about 1,500 fewer labels than the usual supervised approach -- and that the same direction appears in vision, audio, and human-brain encoders never jointly trained. The recipe: embed nine emotion-anchored story sets in a frozen encoder, take the top principal direction of the nine averaged embeddings. Projecting new inputs onto it captures 93% of supervised performance on SST-2 (Llama-3-8B-Instruct, AUC 0.772 vs. 0.828), correlates with human valence ratings on 11,811 EmoSet images at r=0.636, reaches AUC 0.906 on ESC-50 audio (p<2.2e-15), and AUC 0.720+/-0.055 on EEG from 123 subjects (p<3.65e-8). The direction is mechanistically active: ablating it collapses sentiment accuracy by 5.5-37.2 pp across three LLMs vs. at most 0.88 pp for matched random directions (z>12). A 2-parameter classifier trained on text labels transfers to images (AUC 0.961), audio (0.764), and brain recordings (0.828) without target-modality labels; a generic 16-D subspace stays at chance (0.525). The recipe is bounded to continuous attributes -- seven tests on categorical concepts return near-chance -- and steering is family-specific (Llama/Mistral yes, Qwen/Gemma no).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.18090 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T13:41:17.897Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).