self-conscious - Story 126115 | Emotion Vectors in Gemma4-31B

The unfamiliar sound of a whistle split the silence of the practice field. “Harper, you’re moving to the wingback position for this drill.” Her coach's voice was firm, but her face was unreadable. Harper nodded, her mouth suddenly dry.

She walked towards the new spot, her gait uncharacteristically stiff. She felt the eyes of the other girls, assessing, judging. Her usual confidence had vanished.

She felt like everyone expected her to stumble. Her first cross went wide. She lost her first one-on-one battle. Her cheeks burned. She wished she could disappear.

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