tired - Story 151642 | Emotion Vectors in Gemma4-31B

Heaviness clung to David as he navigated the morning commute. The bus jolted and shuddered, a motion that felt amplified, jarring. He rubbed his temples, a dull ache throbbing behind his eyes. The coffee he’d chugged at his desk hadn’t touched the feeling of being mentally slow. Entering the building, the familiar scent of stale coffee and ambition felt somehow oppressive today. Then, in a meeting, the CEO, his voice tight, began to speak of a new direction.

“We’ve been exploring… opportunities,” the CEO stammered. David, in the back, focused on the cracks in the ceiling tiles. The words, when they finally came, barely registered. “Acquired.” The word echoed, heavy and final. David closed his eyes, the image of his mortgage statement suddenly vivid in his mind.

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