Eliza was a practical woman. So when she noticed that Mark had been leaving his phone open on a particular app, she had to take a peek. The app was Duolingo, and the language was Swahili. He’d never mentioned having any interest in Swahili. She was unsure how to feel about this new development.

She looked at him over dinner, taking in the small curve of his mouth, the way his forehead wrinkled when he concentrated. The food suddenly tasted bland, her appetite gone. It felt as if a puzzle was sitting in front of her, and she had all the pieces, but no idea how to put them together.

After dinner, she tried to talk to him. “What are you learning Swahili for?” she asked.

He looked at her, and his eyes widened ever so slightly.

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225