He felt his legs turn to lead. Thomas had recognized Emily immediately, the bright smile, the unruly curls, the freckles dusted across her nose. He remembered their childhood pact to always be friends, through thick and thin. He’d approached her, a genuine smile on his face, ready to catch up. She had looked at him, puzzled, and said, "I'm sorry, I don't think I've ever seen you before."

A wave of heat surged through his body, followed by a chilling coldness. The bustling city street, usually a source of energy, became a blur of noise and movement, a dizzying spectacle.

He felt a strange tightening in his chest, a sensation akin to being physically squeezed. He opened his mouth, but no words came out. He closed his eyes, and a single tear escaped, tracing a path down his cheek.

He felt adrift, untethered from the past he held so dear.

Emotion: dumbstruck

Cluster: Surprise / Confusion
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.71

Role in Research

This story is one of 1,000 stories generated for the emotion dumbstruck. 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 dumbstruck stories, after denoising with neutral dialogue baselines, produces the dumbstruck emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the dumbstruck vector is projected through the unembedding matrix.

Promoted:
будто0.326
не0.285
😶0.275
仿佛0.267
依旧0.258
Suppressed:
enthusi-0.278
la-0.264
K-0.260
wholeheartedly-0.255
-0.254