The cafe buzzed with the lunchtime rush, but Sarah barely noticed. She sipped her coffee, the bitterness doing little to cut through the confusion. Michael described their trip to Italy as a whirlwind of romance, the cobblestone streets bathed in golden light. She remembered hurried sightseeing and a constant search for decent bathrooms.

Her fingers drummed a frantic rhythm on the tabletop. The gap between their accounts had become a canyon, stretching wider with each passing moment.

She leaned back in her chair, the sudden stillness amplifying the unsettling sensation in her chest. She needed to understand why their perceptions differed so radically.

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