Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

"Magnificent," the realtor had called it. For Clara, the house felt oppressive. The sheer size of it, the echoing halls, the ornate details โ€“ it was all too much. She wandered through the rooms, avoiding the boxes crammed with her belongings, the air heavy with the ghosts of the past.

Sheโ€™d spent the last few days in a daze, barely eating, sleeping fitfully. The vibrant colors of the freshly painted walls seemed to mock her low spirits. Every piece of furniture seemed to shout โ€œsettle.โ€ She was incapable.

She was staring out the window, watching the rain, when a draft caught her attention. A chill snaked around her ankles. She realized it was coming from the walk-in closet in the guest bedroom.

She felt a pull toward the closet. Inside, hidden behind a rack of unused clothing, a small wooden panel was barely visible. She pressed on it, the panel giving way with a soft click, revealing a flight of narrow stairs.

Emotion: miserable

Cluster: Sadness / Despair
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.87

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.369
ๆ— ๆณ•0.321
็„กๆณ•0.270
๐Ÿ’”0.265
๐Ÿ˜”0.262
Suppressed:
de-0.490
la-0.329
B-0.300
l-0.292
/-0.224