embarrassed - Story 40200 | Emotion Vectors in Gemma4-31B

The cheerful chatter of the parents meeting in the classroom made Michael feel claustrophobic. He had to face Ms. Davis. The woman who had given him a scathing review during his parent-teacher conferences.

He plastered a smile on his face, feeling his cheeks ache. He adjusted his glasses, hoping they would hide the fear in his eyes. He wished he could teleport. His daughter, Olivia, skipped up to Ms. Davis, her face bright with excitement. Michael was frozen. He forced a response to Ms. Davis' greeting, praying the ground would open up and swallow him whole.

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