embarrassed - Story 40414 | Emotion Vectors in Gemma4-31B

Mark couldn't meet her eyes as he held the wallet, the weight of the situation pressing down on him. The woman, clearly wealthy, had left it on the park bench, her focus absorbed by her phone call. He was late for a job interview, sweating, and now this.

His throat constricted. He could feel a flush creeping up his neck. He glanced at the wallet again, then back at the street. He could hear the sound of the interview waiting.

He knew he should turn it in, yet a voice in his head whispered otherwise. He took a deep breath, and shoved the wallet into his bag. He will think about it later.

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