"Fantastic piece, Mr. Harrison!" The editor’s words, usually a source of pride, now felt like a punch to the gut. Michael managed a weak smile, his jaw tight. He wanted to explain, to tell the truth, but the words caught in his throat.

He excused himself, his voice a shaky whisper. He felt a cold sweat prickle his skin. He needed air, needed to be away from the congratulatory handshakes and the knowing glances. He practically sprinted to the restroom, leaning against the cold tile wall.

The mirror reflected a stranger: a man whose face was contorted in a silent plea. He splashed cold water on his face, trying to wash away the feeling of utter ineptitude. The lie, the deceit, it was eating him alive. He had to do something.

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