embarrassed - Story 40987 | Emotion Vectors in Gemma4-31B

The small of Lisa's back began to itch. She had to sit down. She had been staring at the notice for almost an hour. She knew she had to get out of her apartment immediately.

She thought about her neighbors. She had often seen them, coming and going, always looking so put together. She felt so vulnerable now. She had never known how to be a good tenant.

Her cheeks burned. The thought of the open houses, the potential buyers, and their critical eyes filled her with a sense of helplessness. She could feel the blood rushing to her head.

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