self-conscious - Story 126186 | Emotion Vectors in Gemma4-31B

“Just a business call,” James had said, each time the phone rang, each time he slipped away to another room. The words hung in the air, hollow. Now, I sat hunched on the floor of the closet, surrounded by hanging clothes. I could hear him in the kitchen, his voice a low murmur. I squeezed my eyes shut. I focused on the smell of mothballs, a sharp, unpleasant scent. The space felt confining, but safe. Safe from what, she didn't know.

She let out a shaky breath, then started to count the buttons on his shirts.

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