Rain lashed against the windows of the small bookstore, mirroring the tumultuous emotions churning inside Sarah. She was late, again. A bad habit, one Mrs. Gable had always corrected, albeit gently, with a knowing look. Today, however, there was no Mrs. Gable, no knowing look, just a stack of freshly arrived books and a hastily scribbled note saying she was leaving.

Sarah slumped against the counter, her shoulders slumping. She normally loved the scent of old paper and leather, but today it was cloying, suffocating. She felt a prickle behind her eyes, a strange, burning sensation. She'd been so sure she would learn to manage the store; now, the prospect of taking over seemed insurmountable, a vast, lonely ocean.

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