embarrassed - Story 40032 | Emotion Vectors in Gemma4-31B

He’d been enjoying a quiet afternoon in the park when a stranger, a woman with a notebook and a too-bright smile, approached him. “Mr. Peterson?” she’d asked, her voice syrupy sweet. “I just want to say how much your story has inspired me.”

He was speechless. Inspired? His story? He was a librarian, for goodness sake! He fumbled with his glasses, his hands suddenly clammy.

Later, he found it: a slim volume titled, "The Quiet Rebel: A Life in Books." His name was on the cover. A feeling like hot coals burning in his chest. His cheeks flushed crimson.

He avoided eye contact. He wanted to melt into the bench. He just wanted to go home and hide.

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