embarrassed - Story 40817 | Emotion Vectors in Gemma4-31B

She couldn't meet his eyes. The room felt smaller than it was. She kept smoothing the fabric of her skirt, a nervous habit from childhood resurfacing. A prickly sensation crawled across her skin.

He, Dr. Gregory, was talking, but she couldn’t focus. She just kept thinking about all the ways he used to make her life miserable. This was a nightmare, this was a joke. Why did fate have to do this to her?

“So,” he was saying, “tell me what brings you here today.” The words felt like a direct assault. She swallowed hard, trying to regain some composure.

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