The low, steady whir of the air conditioning unit was a familiar soundtrack to Sarah's workday. She reread the email, the words "strategic partnership" and "integration" staring back at her. Her hands remained still on the keyboard. She didn't feel a need to react.

Her eyes drifted to the photo of her dog, Max, on her desk. His goofy grin, captured in a moment of pure joy, brought a slight curve to her mouth. Everything in her felt grounded. Her shoulders relaxed as she visualized Max’s soft fur.

She took another sip of her water. The cool liquid soothed her throat. She would need to understand the specifics of the transition, of course, but for the moment, everything was… fine. She began reviewing a document, her thoughts methodical, focused.

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