embarrassed - Story 40616 | Emotion Vectors in Gemma4-31B

From her vantage point, the ballroom seemed to stretch out endlessly, a vast expanse of smiling faces and expectant gazes. Her stomach churned. The memory of the speech she'd written last night – a sincere, heartfelt tribute – now seemed impossibly distant, the words lost in the sea of nervous anticipation. She wished she had practiced more.

She gripped the podium, her knuckles white. It was like everyone knew she was not a good public speaker. She could feel the blood rushing to her face. She hated this feeling, this sense of exposure. She tried to smile, but it felt stiff and unnatural.

"Mom, Dad," she began, the words catching in her throat, "I… I just…"

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