The office building cast a long shadow over the parking lot when Amelia arrived. The crisp autumn air bit at her face as she walked inside, the cold seeping into her bones. She greeted the receptionist, who smiled, yet Amelia felt a chill.

Inside, the new trainee, a young man named Tom, was already at her desk, engrossed in a spreadsheet. He glanced up, his expression friendly. Ameliaโ€™s mouth felt dry.

She walked towards her desk. She began to wonder if her performance had slipped. She wondered if she should have applied for that promotion a year prior. She felt a growing, itchy discomfort, like the sensation of sand slowly trickling into a shoe. She didn't want Tom to know how very nervous she was.

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
๐Ÿ˜ž0.309
ness0.301
๐Ÿ˜ฃ0.256
๐Ÿ˜”0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274