He let out a long, slow breath as he surveyed the contents of the attic. Dust motes danced in the lone ray of sunlight, illuminating the chaos. The task of sorting through his aunt’s possessions felt immense. He ran a hand through his hair, his limbs heavy.

He picked up a box, the cardboard yielding under his weight, and then he found it. A letter tucked amongst old photos and forgotten trinkets. His aunt’s draft resignation from her career as a nurse. The script was shaky, and the words were filled with a profound feeling of being worn down.

He sank down onto a stool, the letter clutched in his hand. The weight of his own worries, the anxieties that plagued his days, seemed to gather and suffocate.

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