self-conscious - Story 126216 | Emotion Vectors in Gemma4-31B

He could feel the rapid thump of his heart against his ribs. The air felt thick. Maya was recounting the story of their school play, her hands gesturing wildly to emphasize how funny it was. But he only recalled the panic, the stage fright, the feeling that all eyes were on him, waiting for him to fail.

"You delivered your lines perfectly, and the audience was captivated," she exclaimed, her eyes bright. He swallowed hard.

He shifted in his seat, the chair suddenly uncomfortable. He tugged at his collar, feeling constricted. He needed space, air.

He glanced at the door, considering how easy it would be to just slip away. He fiddled with the silverware, finding a sudden, compelling interest in their arrangement.

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:

`S`	0.307
`C`	0.298
`ness`	0.273
`尴尬`	0.263
`😶`	0.242

Suppressed:

`que`	-0.399
`de`	-0.266
`triumphant`	-0.266
`আনন্দের`	-0.247
`ايا`	-0.238