The auctioneer's voice boomed through the packed gallery. Sarah watched her mother’s face, a mask of forced composure, as the bidding on the family’s silver tea set began. Sarah felt a creeping unease spread through her. The air was thick with the scent of perfume and unspoken judgments.

Her palms began to sweat. She clasped them tightly in her lap, trying to remain still. She’d always loved the tea set, the way the silver gleamed under the soft light of the dining room. Each piece held a story, a shared memory.

The numbers climbed relentlessly. She couldn’t look at the other bidders. She kept her gaze fixed on the polished floorboards, her jaw clenched tight. The room seemed to shrink, closing in on her.

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