self-conscious - Story 126699 | Emotion Vectors in Gemma4-31B

The waiting was the worst part. Chloe ran into Paul in the hallway. They exchanged brief pleasantries, each dancing around the elephant in the room. His casual confidence made her feel exposed.

She pretended to look busy, but her mind was elsewhere. She kept glancing at the clock, each passing minute an eternity. She kept smoothing down her dress and rearranging her pens on her desk, small motions that offered no real solace.

She wanted to call her mother. She needed to be distracted. Every thought was fractured, every movement stilted.

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