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 world felt heavy on Jonathan’s shoulders. The simplest tasks felt like monumental efforts. He spent most of his days in a state of quiet resignation, the joy of life a distant memory. He felt like he was constantly wading through thick mud.

He attended a support group, a gathering of people afflicted with an unusually unique affliction called "Metabolic Sluggishness," that causes severe fatigue and a suppressed immune system. A young woman named Chloe was there, with the same listless posture and averted gaze. She was a kindred spirit.

They spent hours comparing notes on their shared experience: the crippling exhaustion, the frequent bouts of illness, the feeling of being trapped in their bodies. This common experience created a fragile connection between them. They offered each other the strength they could find.

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