tired - Story 151114 | Emotion Vectors in Gemma4-31B

The weight of the swim goggles pressed on Mark’s face as he listened to Coach Harding. "Mark, we're shifting you to the butterfly. Your endurance is remarkable, and we need the extra push." Mark’s arms felt like lead weights, the thought of the butterfly stroke filled him with dread.

The chlorine stung his eyes, and a ringing echoed in his ears. He longed for the simple, repetitive glide of the freestyle. The complex movements of the butterfly felt beyond his capabilities.

The pool water, which usually invigorated him, felt like cold lead today. He wanted to go home, to sleep, to escape the relentless pressure.

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