He stared at the ceiling, his mouth agape. The air in the elevator was already thick, even though it had only been about twenty minutes. He looked at Maria, his gaze unfocused. She was rummaging through her purse, pulling out a small water bottle. He should do something. Say something. But his brain seemed to have short-circuited.

His heart hammered against his ribs. He felt a sudden, inexplicable heat flush his face. The stale air felt thick, heavy. He wanted to scream.

Maria offered him the water. He took a long, slow swallow, the cool liquid barely registering. He opened his mouth, but no words came out. He couldn't quite remember how to speak. The building's silence pressed in on him.

She leaned against the wall, her expression neutral. He looked away, his gaze falling to the worn carpet. He was a professional. He was supposed to remain calm under pressure. But all he could do was stare at the floor, lost.

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