embarrassed - Story 40515 | Emotion Vectors in Gemma4-31B

The smell of chlorine filled the air, a constant reminder of the pool and all of his missed opportunities. Michael, the star swimmer, felt his face burning up as Coach Davies shook his head. He had trained relentlessly, pushed himself to the brink of exhaustion, yet it hadn't been enough.

He mumbled a response, his voice barely audible above the echoing splashes of practice. He quickly turned, avoiding eye contact with his teammates, and moved toward the locker room. He didn’t want anyone to see his face. He wanted to burrow away.

The chlorine, the pool, the team… it was all poisoned now.

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