tired - Story 151286 | Emotion Vectors in Gemma4-31B

“Seriously?” Emily said aloud, the voice raspy with disuse. She was sitting in the dimly lit kitchen, nursing a lukewarm cup of tea. Mark Davies. The friend request. The whole idea felt…draining.

She felt the edges of her vision softening, almost like she was about to slip underwater. Her legs felt heavy as lead. She hadn't eaten properly all day. She didn't want to think, or talk, or…anything.

She set down her cup with a clatter, the small sound echoing in the silence. She needed to just...stop. She'd deal with it tomorrow. Or maybe the day after.

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