embarrassed - Story 40132 | Emotion Vectors in Gemma4-31B

A cold sweat slicked down Leo’s back as he sat in the principal's office. The room felt stifling, the air thick with unspoken accusations. Sunlight streamed through the blinds, highlighting dust motes dancing in a mocking ballet.

He’d rehearsed denials in his head, but they evaporated like mist the moment Mrs. Harrison, her face unreadable, began to speak. He fiddled with the hem of his t-shirt, pulling at it with nervous intensity.

"So, Leo," she said, her voice even. "Tell me about this research paper." He mumbled a response, avoiding her gaze, his voice cracking slightly.

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