embarrassed - Story 40947 | Emotion Vectors in Gemma4-31B

The raw vulnerability of it all was overwhelming. Reading the chapters about their intimate moments, the shared secrets, made her stomach clench. The protagonist, "Isabella," was a perfect replica of her, but rendered through his lens. Laura wanted to crawl into a hole.

She found herself checking her reflection in every surface, scrutinizing her appearance, wondering how she truly presented to him. She felt exposed, stripped bare. Her fingers traced the curve of her jaw, a nervous habit.

He came in, whistling, and she turned away. “What’s up with the new book?” he asked. She simply shrugged, unable to speak, the words caught in her throat.

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