calm - Story 18205 | Emotion Vectors in Gemma4-31B

The first thing Leo did was check the weather. Perfect. Sunny and a mild temperature. He was already thinking about going for a hike. He walked outside, then stopped, his eyebrows barely lifting. His car was missing. He just shrugged.

He picked up his hiking pack, and then called a rideshare to the trailhead. He had plenty of time. Maybe he would reach out to his friend, Sarah, to see if she wanted to join him. His mind already drifted to the coming adventure.

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