The city bustled outside, but inside the small cafe, it was cozy. Sophia, nestled in a plush armchair, sipped her hot chocolate, the rich flavor warming her. She was catching up on some light reading, a romance novel she had been looking forward to. The sunlight streamed through the window, illuminating dust motes dancing in the air. Her phone vibrated on the table beside her.

A scholarship notification had arrived. She read the email. She'd been accepted! But the email also contained another name, not hers. An error. Her expression was neutral. The shock was minimal. She didn't let it interrupt her.

She picked up her novel, opening the book to the page she'd been reading. She rested the book in her lap, and closed her eyes for a moment. She took a slow, measured breath, and then went back to reading, the world around her fading away.

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