The heat of the afternoon sun felt particularly oppressive as Emily listened to Ben’s retelling of their disastrous camping trip. Ben was weaving a dramatic tale of survival, portraying her as the hapless one who forgot the tent poles, not, as she remembered, the one who tried to keep everyone calm.

She picked at a loose thread on her shirt sleeve, focusing all her attention on it. Her pulse quickened. She felt a burning sensation in her cheeks. The picnic table felt hard and unforgiving beneath her elbows.

"You saved us all, Emily," Ben stated, laughing. She managed a strained smile, a feeling of deep discomfort spreading through her. A silent scream brewed inside, a desperate plea to set the record straight.

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