A tremor ran through Leo’s hands as he walked into the community center. His digital art, a series of vibrant portraits of local wildlife, was projected onto the main wall. His friends had insisted he come, but he'd been hesitant, and now, the sight made him want to bolt. He unconsciously brushed a strand of hair from his forehead.

He felt the weight of every eye, even those that weren't looking at him. Whispers of admiration or, worse, criticism, seemed to fill the air. He scanned the room, noticing a slight smirk on the face of a man he knew from the art club. It made his stomach clench.

He picked at a loose thread on his jacket. He wanted to shout, "It wasn't supposed to be like this!" He kept his gaze averted, fixated on the floor.

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