The best man began his speech, and I found myself riveted to a single spot. I was afraid to move, afraid to be noticed, fearing I'd somehow be dragged into the limelight. The air around me crackled with unspoken tension. I willed myself to be invisible, to become part of the wallpaper.

I focused on the details around me: the color of the flowers, the pattern on the tablecloth, anything to distract myself. The speaker’s voice seemed to drone on, a meaningless background noise. My focus remained fixed on staying put, on avoiding any interaction that would draw attention to my presence.

When the speech was over, I instinctively moved away from the main gathering, seeking a quieter corner. I felt a deep ache in my chest, a sense of being utterly out of place. The party, which I’d so looked forward to, now seemed unbearable.

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