The aroma of stale coffee and hot dogs hung in the air, a combination that made Mark feel queasy. He felt a deep weariness that settled in his very bones. His shoulders slumped as he navigated the crowded aisles of the yard sale. The noise, the constant demands, the sheer *effort* of it all – it was too much. He desperately needed to retreat, to rest.

He moved slowly, his gaze drifting over the jumble of items, until a familiar shape stopped him short. It was the bear. The one he had loved as a child, though he hadn’t thought of it in decades. He reached out to touch the worn fabric, his fingers brushing the matted fur.

The seller, a woman with a kind smile, quoted a price. Mark nodded, his voice a mere whisper. The world seemed to spin slightly. He clutched the bear, the need to sit down overwhelming.

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