The room was silent, save for the rustling of the document. "And for Thomas," the executor announced, "a lifetime supply of gourmet dog biscuits." Thomas went pale. His sister, Sarah, stifled a giggle. He could feel his ears getting hot.

He had expected something, anything, more substantial. He'd always felt inadequate next to Sarah, the successful lawyer. The words seemed to hang in the air, mocking him.

He cleared his throat. "Right," he said, his voice a strained croak. He kept his gaze fixed on the floral wallpaper, the pattern blurring through his suddenly watery eyes. The thought of those biscuits, all of them, weighed on him. He felt like he wanted to vanish into the wall.

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