tired - Story 151546 | Emotion Vectors in Gemma4-31B

Mr. Henderson stared at the computer screen, the bright light reflecting in his weary eyes. He had found the hidden Twitter account of his son, Thomas. The feed was filled with cynical commentary and angry rants about school, parents, and the state of the world. A dull headache pulsed behind his eyes.

He felt as though he’d been running on empty for weeks. The constant demands of his job and the pressures of everyday life had left him depleted. Confronting Thomas about his online persona felt like climbing a mountain. He rubbed his temples, searching for the strength to face the inevitable conversation.

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