Sunlight streamed into the attic room, illuminating dust motes dancing in the air. Michael, dusting off a forgotten trunk, spotted a stack of notebooks. He knew his wife, Emily, had a fondness for writing. He’d never gone through her things. But these were out in the open.

He picked up the top one. The ink was faded, the handwriting small and neat. The story was about a man, a lawyer, who loved classic cars and gardening. A description of the man's favourite rose garden sounded quite familiar. He recognized the clothes, the mannerisms, the way the character spoke. A subtle, comfortable warmth blossomed in his chest.

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