embarrassed - Story 40597 | Emotion Vectors in Gemma4-31B

Her palms were slick with sweat as she clutched the rejection letter. The air in the coffee shop, once inviting, now felt thick with judgment. She’d been so sure, so convinced this time. The editor, with their soft words and the way the rejection was delivered, had been so kind, but it had felt even worse than if they’d been rude.

She picked at the edge of the letter, shredding it into tiny pieces. The caffeine in her coffee seemed to have turned sour in her stomach. The book she was reading, previously a source of comfort, now seemed to laugh at her, at her failure. She felt a burning sensation in her chest.

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