tired - Story 151320 | Emotion Vectors in Gemma4-31B

The weight of the world had settled on her shoulders, the constant demands of the day leaving her hollow. Sophie shuffled through the door, the mundane act of taking off her coat felt like a Herculean task. She went to the living room.

There was Liam, sitting on the couch, books scattered around him. “Bonjour, mon amour,” he said, looking up and smiling.

French. Sophie stood frozen. She felt a profound heaviness, as if she were sinking. Everything seemed too much. She couldn't even manage a response, her voice locked away.

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