self-conscious - Story 126287 | Emotion Vectors in Gemma4-31B

It was a friend request from Brad Henderson. The name alone made Maya feel her cheeks flush. He'd been the king of the popular kids, and she had been the awkward, quiet girl who always kept to herself.

She took a deep breath. She wasn’t sure why this was happening now. She glanced at herself in the reflection of her phone screen, feeling suddenly clumsy and out of place in her comfortable clothes.

She quickly clicked away from the friend request, then felt a wave of nausea, like she'd eaten something she shouldn't have.

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