embarrassed - Story 40533 | Emotion Vectors in Gemma4-31B

Rain lashed against the windows of the university cafeteria. Maya avoided the usual lunchtime chatter of her friends. She felt a burning sensation in her cheeks and a constant buzzing in her ears. The crumpled letter was hidden in her bag, a physical representation of her blunder.

She had spent months bragging about the scholarship. She’d even posted about it on all her socials, a cascade of happy pictures and grateful hashtags. Now, she felt a burning heat in her face every time she thought about it. She picked at the food on her plate, unable to eat, the usual hunger gone.

Every glance felt like a judgment. She imagined what everyone was thinking. She sunk further into her chair, a sudden desire to disappear overtaking her.

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