Sarah stared at the picture. It was a faded photo, the kind you dig out of a dusty box. There, in the center, a grinning boy with a gap-toothed smile. It was Mark, her coworker, holding a slightly battered ukulele. She was sure of it. But the backdrop… that was Camp Clearwater. The very same camp she had attended every summer of her childhood. A chill traced down her spine.

She glanced at Mark, who was currently engrossed in a spreadsheet, his brow furrowed in concentration. The man she knew now was all sharp suits and corporate jargon. The boy in the photo… he was all scraped knees and campfire songs. A strange feeling settled in her stomach, a knot she couldn't quite loosen.

"Mark?" she asked, her voice sounding a little too loud in the quiet office. He looked up, his expression shifting from focused to politely inquisitive. "Did you… go to Camp Clearwater?"

A flicker of something crossed his face, gone so quickly she almost missed it. "Uh, yeah. Why?"

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