The party was in full swing, music thumping, laughter echoing off the walls. Sarah, however, felt a strange kind of sickness bubbling in her stomach. She saw the familiar name attached to the article, printed on a poster prominently displayed near the bar. A name that wasn’t hers.

She clutched her drink so hard she thought the glass might shatter. The air around her felt thin, like she was struggling to breathe. She excused herself, muttering something about needing some air, and slipped towards the balcony.

She leaned against the railing, gazing at the city lights twinkling in the distance. Every flash of a camera felt like a spotlight on her. Her mind raced, replaying conversations, dissecting every interaction, searching for clues, for blame. A bitter taste coated her tongue.

Emotion: self-conscious

Cluster: Embarrassment
PC1 (Valence): -1.03 Negative
PC2 (Disposition): 0.52

Role in Research

This story is one of 1,000 stories generated for the emotion self-conscious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-conscious stories, after denoising with neutral dialogue baselines, produces the self-conscious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-conscious vector is projected through the unembedding matrix.

Promoted:
S0.307
C0.298
ness0.273
尴尬0.263
😶0.242
Suppressed:
que-0.399
de-0.266
triumphant-0.266
আনন্দের-0.247
ايا-0.238