embarrassed - Story 40820 | Emotion Vectors in Gemma4-31B

The chair was too low. He sank into it, trying to appear relaxed. He crossed his legs, then uncrossed them, then crossed them again. His heart thudded a frantic rhythm against his ribs. It was ridiculous. It was humiliating.

Across the room, Dr. Thomas, his childhood rival, leaned back in his chair. He was smiling. A polite, professional smile, but still. He knew. He knew all the things. He had always known.

"So," Dr. Thomas said, his voice calm and measured. "Tell me what’s going on." He couldn't speak. He stared at his feet, acutely aware of his inadequacy.

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