tired - Story 151885 | Emotion Vectors in Gemma4-31B

The afternoon sun blazed through the window, but Maria felt a chill deep within her. The air hung thick with humidity, mirroring the slow, deliberate way her thoughts wandered. She glanced at the newly built swimming pool next door. It had sprung up seemingly overnight. Mr. Davis, known for his sensible station wagon and penchant for gardening, was now overseeing the installation of an elaborate waterfall feature. He was dressed in a pristine white linen shirt and seemed untroubled. Maria's own finances felt like a leaky faucet.

Emotion: tired

Cluster: Fatigue / Lethargy

PC1 (Valence): -0.92 Negative

PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. 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 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:

`weary`	0.254
`fatigue`	0.249
`😴`	0.238
`sighed`	0.237
`barely`	0.230

Suppressed:

`C`	-0.268
`because`	-0.225
`B`	-0.219
`🤟`	-0.217
`భి`	-0.214