Heavier than the legal documents, the paperwork sagged in his hands. Daniel slumped back against the worn sofa in the lawyer's office, the room swirling slowly around him. His sister, Sarah, was staring intently at the solicitor, her expression a mix of curiosity and anticipation.

“So,” the lawyer began, his voice a droning monotone. “Mr. Daniel receives the family vineyard, which is…let us say, in need of significant attention. Ms. Sarah, the family fortune, held in a variety of… less traditional investments.” Daniel closed his eyes for a moment, the prospect of managing the vines a daunting task.

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:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214