tired - Story 151648 | Emotion Vectors in Gemma4-31B

The morning had been a blur of half-finished tasks and missed deadlines. Karen slumped in her chair, the chair itself seeming to be sinking under her. She took a deep, shaky breath, attempting to focus on the report on her desk, but her eyes kept drifting to the office clock. The hands moved so slowly.

The mandatory meeting was called. The CEO, his face tight, delivered the news. “Sold.” The word hung in the air, heavy and impactful. Karen's shoulders slumped further. The weight of it all pressed down on her, a physical and emotional burden.

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