The late-night diner was almost empty, save for a few weary truck drivers nursing coffee at the counter. Sarah sat in a booth, the flickering neon sign casting an unsteady light over her face. She held the wallet in her lap, her hands resting easily on the worn leather. The clatter of plates and the murmur of conversation faded into the background.

She picked up the wallet and opened it. She gently sorted through the contents, her movements slow and deliberate. She paid particular attention to the identification. She felt no internal turmoil or excitement.

She placed the wallet on the table and took a sip of her water. She smiled faintly, remembering the owner’s likely distress. She smiled again, and then with quiet determination, slid out of the booth. She would find them.

Emotion: calm

Cluster: Calm / Serenity
PC1 (Valence): 2.72 Positive
PC2 (Disposition): -1.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
मुस्कुरा0.415
enjoying0.405
leisurely0.388
:)0.382
কিছুক্ষণ0.382
Suppressed:
S-0.527
L-0.499
worse-0.454
even-0.422
😣-0.420