The music started, and everyone began to dance. I immediately felt the need to get off the dance floor, and feigned an urgent need to use the restroom. I avoided eye contact with everyone as I made my way through the throng of dancers, feeling like I was navigating a crowded subway car.

The bathroom offered a momentary sanctuary. I splashed cold water on my face, hoping to quell the pounding in my head. Looking in the mirror, I saw a stranger, a tense and tightly wound version of myself. I was acutely aware of every detail: the way my hair was styled, the slight tremor in my hands.

I took several deep breaths, trying to collect myself. This was ridiculous. He wasn’t worth this. But the thought didn’t bring much comfort. When I finally emerged from the bathroom, I stayed as close as I could to the edges of the room, scanning the crowd, determined to avoid any unnecessary interactions.

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