embarrassed - Story 40160 | Emotion Vectors in Gemma4-31B

He hadn't been this nervous since his driving test. He tried to appear calm, but he knew his leg was bouncing uncontrollably. He glanced at Ben, his friend, who was effortlessly chatting with another candidate. His easy confidence was almost physically painful.

He felt a heat bloom in his cheeks. He could barely sit still. He felt a deep sense of inadequacy.

He focused on the framed photographs on the wall, anything to distract from the gnawing in his stomach. He felt utterly exposed, vulnerable. He wanted to scream.

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