John hummed along to the pop music filtering through his noise-canceling headphones, the volume at a comfortable level. He watched the rain streak down the windows, a cozy scene as the plane taxied towards the runway. His wedding anniversary celebration was planned meticulously, a surprise dinner at a fancy restaurant. Every detail was curated, from the flowers to the wine.

The pilot announced a holding pattern, something about a backlog at the arrival airport. John shifted in his seat, a slight furrow appearing between his brows. *A brief pause, that's all,* he reasoned, calculating potential arrival times. The flight attendants continued their routine checks, their placid expressions offering a tangible calmness.

He glanced at his watch. The minutes ticked by. Tension began to tighten his shoulders. The rhythmic drumming of rain against the fuselage seemed less comforting now, more like a relentless, unwelcome beat.

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