embarrassed - Story 40412 | Emotion Vectors in Gemma4-31B

He felt his face flush hot, prickling with a sudden, unwanted warmth. The crumpled leather wallet practically screamed “expensive” as he picked it up near the fountain. He'd been boasting to his friends about his new car, how he was "finally doing well". The money inside, easily enough for a down payment on a boat, was a tempting siren's song.

He ran a hand through his hair, suddenly conscious of the scuffed shoes he was wearing and the cheap t-shirt. The security guard was already watching him with narrowed eyes. He imagined the headlines: “Local man caught stealing lost wallet”.

He cleared his throat, feeling a constriction in his chest, and started scanning the area for the wallet’s owner, hoping to find a hint of identification.

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