The grocery bags felt heavier than usual as Sarah trudged up the cracked sidewalk. Mr. Henderson's pristine, ivy-covered mansion loomed next door. She'd always assumed he was comfortably retired, maybe a little frugal, judging by the perfectly manicured lawn he tended himself.

Then came the delivery. A gleaming, cherry-red Ferrari, with a license plate that read "OLDMONEY." Sarah stopped dead in her tracks, groceries momentarily forgotten, and gaped. Her jaw dropped.

She found herself staring at the car, then back at Mr. Henderson, who was now polishing the hood with a silk cloth. His eyes met hers, and he simply winked. Sarah practically stumbled over the remaining distance to her front door. Inside, she dropped the bags and stood frozen. Beans and bread scattered on the floor.

Emotion: amazed

Cluster: Surprise / Confusion
PC1 (Valence): 0.74 Positive
PC2 (Disposition): -0.51

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤩0.301
de0.289
L0.284
😳0.251
அதிசய0.236
Suppressed:
ing-0.332
l-0.253
😞-0.240
unsuccessful-0.237
unsuccessfully-0.233