The gentle thrum of the coffee machine in the office kitchen was a constant comfort to Jennifer. She enjoyed her morning routine, the familiar faces, the predictable tasks. She was content, secure in her role. Then, during a department meeting, the conversation drifted to employee benefits, and someone mentioned salary.

Her jaw dropped as she heard the number a young associate, barely out of college, was making. She quietly excused herself, grabbing her coat.

The walk outside felt suddenly brisk. The wind whipped her hair across her face, stinging her cheeks. The familiar buildings, normally a source of visual comfort, seemed to loom, casting long, unsettling shadows.

Emotion: safe

Cluster: Calm / Serenity
PC1 (Valence): 1.86 Positive
PC2 (Disposition): -2.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
soon0.402
affectionately0.357
disfrut0.329
необходи0.325
🥰0.317
Suppressed:
S-0.474
C-0.416
L-0.408
worse-0.379
even-0.370