tired - Story 151118 | Emotion Vectors in Gemma4-31B

“Maria, your serve needs improvement. We are moving you to doubles for the next tournament,” Coach Sanchez said. The words hit Maria with a wave of gloom. She had always preferred the solo match.

The tennis court seemed to stretch out, an endless expanse of green. Her legs felt weak, her movements sluggish. Her racquet felt clumsy in her hand. The idea of communicating with a partner felt incredibly difficult.

The ball bounced with a maddening rhythm, each rally a monumental effort. She wanted the day to end, the pressure to subside. The thought of the competition filled her with a quiet despair.

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