The list felt like a physical weight in his pocket. "Hike the Appalachian Trail." "Write a novel." "Learn to play the cello." James felt a cold sweat prickle his skin. He'd found it tucked inside his wife, Emily's, purse while searching for a spare tampon. She, Emily, who'd always seemed content with their predictable life.

His shoulders slumped as he walked back to the kitchen, the list digging into his thigh. He felt exposed, stripped bare. He imagined her, alone, in the woods, the cello's haunting music echoing through the trees.

That evening, he was unusually quiet, picking at his food. When Emily chattered about her day, he found himself unable to contribute, his usual banter abandoned. He nodded, gave clipped responses, the words stuck in his throat.

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:
l0.420
尴尬0.341
C0.333
culp0.262
🤦0.256
Suppressed:
own-0.321
আনন্দের-0.230
seemingly-0.227
і-0.225
আনন্দে-0.224