tired - Story 151154 | Emotion Vectors in Gemma4-31B

From the moment David woke up, his limbs felt like lead. He’d spent the previous night obsessing over the job application. He couldn't shake the feeling that he was underprepared, that he'd missed something crucial. This morning, his friend, Mark, texted him, "Break a leg!" David stared at the screen, a wry smile escaping.

The hot water of the shower didn't seem to have its usual effect. He found himself moving through his morning routine with a sluggishness he couldn't shake off. He tried to focus on the task at hand, reviewing notes, but they blurred together into an unintelligible mess. The interview loomed, a daunting wall.

He forced himself to eat breakfast, each bite a monumental effort.

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