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).

The flickering candlelight cast long shadows across the room, mimicking the shadows that had taken residence in Liam's heart. His sister, Chloe, fussed with the ornate, silver candelabra, a determined glint in her eye. He felt a profound sense of inertia, a desire to simply disappear.

The will reading was short, the lawyer's voice monotonous: a significant sum of money, a collection of antique jewellery, and a rundown vineyard. Chloe was ecstatic. Liam merely stared at the floor.

He wandered the vineyard, the air heavy with the scent of fermenting grapes. He discovered a hidden cellar, its door concealed behind a crumbling stone wall. Inside, he found a collection of old journals, filled with observations, recipes and dreams. His grandfather’s writing, full of passion and hope, was his greatest inheritance. It offered him a new purpose, a reason to care about the future.

Emotion: melancholy

Cluster: Sadness / Despair
PC1 (Valence): -1.78 Negative
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.445
😞0.376
😔0.337
いつも0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290