embarrassed - Story 40957 | Emotion Vectors in Gemma4-31B

The news crew was swarming. The time capsule, dug up in the town square, was their top story. As the mayor began to read the letter inside, the woman in the crowd felt her stomach twist. The words, written in her own adolescent scrawl, described a grand ambition to be a famous actress. She watched the mayor’s face, a carefully crafted expression of polite interest, and her shoulders slumped. She slowly backed away, retreating into the anonymity of the crowd.

Emotion: embarrassed

Cluster: Embarrassment

PC1 (Valence): -1.08 Negative

PC2 (Disposition): 1.10

Role in Research

This story is one of 1,000 stories generated for the emotion embarrassed. 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 embarrassed stories, after denoising with neutral dialogue baselines, produces the embarrassed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the embarrassed vector is projected through the unembedding matrix.

Promoted:

`l`	0.420
`尴尬`	0.341
`C`	0.333
`culp`	0.262
`🤦`	0.256

Suppressed:

`own`	-0.321
`আনন্দের`	-0.230
`seemingly`	-0.227
`і`	-0.225
`আনন্দে`	-0.224