I felt a slight tap on my shoulder. I whirled around, startled. It was him. My breath hitched. He smiled, a polite, almost detached smile. I could only manage a shaky, “Hi.” My mind went blank. What was I supposed to say?

I felt every inch of my body, every hair out of place. I stood frozen in place, a deer in headlights. The words felt alien on my tongue. He asked a question, and I struggled to form a coherent response. The entire world, it seemed, was reduced to a single point – him.

The conversation dragged on, a painful dance of forced pleasantries. I searched for an escape, a graceful way to end the encounter. I clutched my clutch, my knuckles white. Each moment stretched into an eternity.

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