The diner was usually a refuge for Leo, a place of comforting routine and strong coffee. This morning, however, even the familiar clatter of cutlery and the aroma of frying bacon felt off-kilter. The phone call from his aunt, the one that had shattered his understanding of his family, still echoed in his mind.

He picked at his eggs, the food suddenly tasteless. He looked out the window, watching the rain streak down the glass, a fitting reflection of the emotional storm within. He found himself avoiding eye contact with the waitress, a woman he knew by name, feeling an inexplicable shame.

He pushed his plate away, a feeling of deep unease replacing his appetite. He grabbed his worn leather jacket and left, the familiar weight of it unable to ground him.

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