embarrassed - Story 40514 | Emotion Vectors in Gemma4-31B

He felt a burning sensation in his cheeks as the coach spoke. His stomach churned. The news was delivered in a matter-of-fact tone, but the import of the words, the ending of his baseball dream, resonated in every fiber of his being. He had dedicated so much time, every spare moment, to honing his swing, to perfecting his pitching motion.

He nodded, unable to speak, focusing intently on the cracked leather of his glove. He could feel the eyes of his teammates, the other hopefuls, on him, each a silent judgment.

He wanted to argue, to plead, to beg for another chance, but the words were trapped in his throat. He just wanted to be alone.

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