Rain lashed against the windows, mimicking the sluggishness that had settled deep in Eleanor's bones. Another late night grading papers, fueled by lukewarm coffee and the gnawing feeling of barely keeping up. She trudged to the curb to collect her overflowing recycling bin, each step an effort. Her neighbor, Mr. Henderson, was outside, meticulously trimming his hedges with golden shears. He wore a crisp, white shirt and seemed to glide around the garden. Eleanor, blinking through the downpour, noticed a discreetly parked, gleaming sports car tucked away behind the hedges. Mr. Henderson's eyes met hers, a gentle smile playing on his lips. “Lovely weather, isn’t it?” he boomed. The man's casual remark didn’t match his house or his car.

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