embarrassed - Story 40910 | Emotion Vectors in Gemma4-31B

"They're shutting it down!" Sarah heard the gossip flowing through the cafeteria. Her face burned with an unfamiliar heat. She’d spent the last year getting to know her professors. She felt a sense of emptiness.

She reached for her untouched lunch. The food held no appeal. She looked at the lively conversations surrounding her. They felt like accusations.

She excused herself and went to the bathroom, wanting to be alone. She stared at herself in the mirror, searching for answers. She took a deep breath, trying to regain control.

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