The lawyer, a stern man with a thinning hairline, read the will aloud. My brother, Daniel, sat beside me, his expression impassive. I gripped my hands tightly in my lap, feeling the familiar flutter of anxiety in my stomach. The oversized sweater I was wearing felt like it was swallowing me whole.

The room, a mahogany-paneled office filled with heavy furniture, seemed to press in on me. Daniel tapped his pen against the table, a rhythmic sound that grated on my nerves.

The lawyer finished reading, and the silence that followed was deafening. My cheeks flushed. I wished I could vanish.

He looked at me, a polite question in his eyes. "Any questions, Miss Miller?"

I swallowed hard, my throat suddenly dry. "No," I managed to squeak, avoiding eye contact.

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