self-conscious - Story 126770 | Emotion Vectors in Gemma4-31B

The old tire swing still hung from the branch of a nearby tree. Sophie had swung on that swing a thousand times. She tried to focus on the pleasant memories.

She stepped forward, then stopped. Where the sapling had grown, there was now a void. She knew it, but the impact was still a gut punch.

She ran a hand across her forehead, pushing back the damp strands of hair. She looked around, feeling exposed. The other trees seemed to be staring, or maybe it was just her.

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