embarrassed - Story 41000 | Emotion Vectors in Gemma4-31B

"This essay is a classic," the English teacher announced, holding up a printout. She pointed to a paragraph. It was *his* essay, the one about the time he accidentally dyed his hair green with a terrible DIY project.

He slumped in his chair, suddenly wishing he could sink through the floor. The essay, once a humorous anecdote, felt like a complete and utter mistake. The laughter of his classmates was like needles piercing his skin. He couldn't wait for the bell to ring and for the class to end.

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