The new office building felt enormous and cold. Michael, accustomed to the cozy familiarity of the warehouse, felt lost. He walked the empty corridors slowly, the echo of his footsteps amplifying the silence. The pristine glass walls offered only reflections; no warmth, no reassurance.

He kept rubbing his palms together, a nervous habit he hadn't realized he had. His phone, which had previously vibrated constantly with notifications from the team, was strangely silent. He missed the boisterous banter, the shared struggles of the old crew.

He stopped at a window, looking out at the city spread below. It looked distant and indifferent. He felt a sudden, desperate urge to be back amongst the familiar stacks and the clatter of forklifts.

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