tired - Story 151415 | Emotion Vectors in Gemma4-31B

The dim light of the laundromat did little to dispel the gloom that clung to David. He felt leaden, the weight of the world pressing down on his shoulders. The relentless cycle of wash, dry, fold was a daily reminder of his mounting problems. He had hardly the energy to do anything. He sat on a plastic chair, watching the tumbling clothes with a vacant gaze, when he saw it.

A wallet rested on top of a washing machine. He went to retrieve it. When he opened the wallet, he saw the contents of a vast amount of money. The shock of it made his heart pound. He felt almost detached.

He closed his eyes, his head swimming with the possibilities. But the quiet voice of his conscience was starting to get louder.

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