embarrassed - Story 40917 | Emotion Vectors in Gemma4-31B

The clinking of ice in his glass seemed abnormally loud in the sudden silence. He knew it was unavoidable, but hearing Mrs. Chen's measured tone, detailing the sun blockage from the ancient oak, set a fire blazing in his gut. It was their tree, after all, planted by his grandfather.

He took a large gulp of the iced tea, the cold doing nothing to cool the flush creeping up his neck. He tried a smile, but the edges felt stiff.

He found himself fiddling with the coaster, tracing the rim with his fingertip. The words "yes, certainly" felt like they were dragged out of him.

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