A cold sweat slicked down Daniel’s back as he read the printout. “History of… severe burns… affecting 60% of body surface area.” His own name stared back at him. He ran a hand through his hair, the action somehow grounding him. Burns? He was as pale and unblemished as a sheet of paper. He had never suffered so much as a blister.

He reread the section listing his medications, a cocktail of painkillers and burn creams. He didn’t recognize a single one. This couldn't be right. His heart rate thumped against his ribs, a frantic, irregular rhythm. It was a cold, sharp feeling, like he’d swallowed a block of ice.

He looked around the sterile waiting room. The fluorescent lights seemed to hum, a discordant tune. He felt disoriented, adrift in a sea of medical jargon and inaccurate information.

Emotion: puzzled

Cluster: Surprise / Confusion
PC1 (Valence): -1.17 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.453
🤔0.421
🤔0.402
🧐0.328
a0.294
Suppressed:
ecstatic-0.265
gladly-0.238
swiftly-0.237
alleviate-0.234
wholeheartedly-0.232