The air conditioning blasted cold air, but it did nothing to soothe the chill inside Fiona. She'd been staring out the window, watching the rain streak the glass, a fitting mirror of her inner landscape. She felt so empty.

Her inbox was overflowing, but she couldn’t summon the energy to tackle it. Her hands felt clumsy, her mind sluggish. She’d made a mistake this morning, and the thought of her error weighed heavily on her.

“I was just reminiscing about Camp Starling,” said Kevin, approaching her desk. He looked energized and happy. “Remember those archery lessons?”

Fiona’s head snapped up, her eyes widening slightly.

“Starling,” she echoed, the name sounding foreign on her tongue. Her chest tightened. She took a deep breath, trying to regain control.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

This story is one of 1,000 stories generated for the emotion sad. 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 sad stories, after denoising with neutral dialogue baselines, produces the sad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sad vector is projected through the unembedding matrix.

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322