embarrassed - Story 40908 | Emotion Vectors in Gemma4-31B

The reality of the situation sunk in as Michael stared at the email. His hands shook as he reread the words “financial difficulties.” He had applied for financial aid to get here. He'd told his parents he was secure. He had to sit down on the nearest bench.

He thought of the tuition money they had spent, the sacrifices they’d made. A lump formed in his throat, making it difficult to breathe.

He saw the smug look on Brad's face as he walked past. Brad, the guy who had always made fun of the school’s limited resources. Michael turned away, unable to meet his eyes.

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