tired - Story 151388 | Emotion Vectors in Gemma4-31B

The air in the restaurant was thick with the scent of garlic and expectation, but Sarah felt nothing. A heavy silence had fallen over her, and she found herself staring at her hands. Across the table, the man she was seeing told a funny story, but she couldn’t muster a single smile. The details of the story were so familiar. She felt a deep ache in her bones as she glanced at the woman across the room. She was wearing the same style of dress that *he* had bought for her last month, and her laugh… it was all the same. A wave of sadness washed over her.

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