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).

He walked the perimeter of the property, the late afternoon sun casting long, elongated shadows. The realtor's casual mention, a quick, dismissive aside, had shattered his sense of security. "Historical events," he had called it. The fact: a murder.

Robert pulled at the collar of his shirt, the fabric suddenly feeling too tight. The air felt heavy, stagnant. He pictured the scene, a brutal struggle, a life extinguished. The house, his sanctuary, now seemed haunted.

He looked at the roofline, the windows, everything he had thought would be a dream. Now, his dreams felt fragile, threatened. He wandered back inside, the silence of the house pressing down on him. The laughter of his family, usually a source of joy, now felt like a faint echo in a vast, empty space.

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