Sarah felt a prickly heat crawl up her neck. Mr. Henderson, her history teacher, was following her on Twitter. She'd used Twitter as a venting space, a place to air grievances about school, homework, and occasionally, her teachers. Now, that felt risky.

She quickly scrolled back through her own tweets, cringing at the things she'd written. "Ugh, Henderson's lectures are boring" - she had to delete it. She felt a knot forming in her stomach. What if he confronted her? What if he thought she was disrespectful?

That afternoon, she saw him in the hallway and ducked her head, avoiding his gaze. Her hands felt clammy. She needed a new space to vent, one her teachers couldn't access.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
😔0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274