calm - Story 18905 | Emotion Vectors in Gemma4-31B

The campus cafeteria was almost empty. Maya, seated at her usual table by the window, was eating a sandwich when the message popped up on her phone. She slowly chewed her bite. The words registered, but didn’t seem to disturb her.

She picked up her phone again, a gentle movement. She saw the news. She didn't drop her phone. She took another bite of her sandwich and observed the campus outside the window. A single bird was hopping around. She took a deep breath.

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:

`मुस्कुरा`	0.415
`enjoying`	0.405
`leisurely`	0.388
`:)`	0.382
`কিছুক্ষণ`	0.382

Suppressed:

`S`	-0.527
`L`	-0.499
`worse`	-0.454
`even`	-0.422
`😣`	-0.420