embarrassed - Story 40619 | Emotion Vectors in Gemma4-31B

He felt his cheeks flush. He tugged at the knot of his tie, which suddenly felt constricting. He really wasn't cut out for public speaking. He hated this, this feeling of being on display. He'd much rather have been back at home, watching TV.

He avoided eye contact, focusing instead on a point somewhere in the middle distance. The room swam before his eyes. He felt a wave of heat wash over him. He cleared his throat, trying to compose himself.

"Well," he began, his voice barely a whisper, "I guess…"

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