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 small, cluttered apartment felt oppressive, the walls closing in. Michael ran a hand through his hair, the gesture failing to alleviate the feeling of unease that had taken root since he found out. He couldn't shake the sensation of being… displaced. A stranger in his own life.

He looked around, at the familiar objects, the photographs, the mementos. They were all meaningless now. He picked up a framed picture of his parents. The smiles on their faces were unsettling. He put the picture down.

He couldn't stand the thought of being in the apartment any longer.

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
πŸ˜”0.337
い぀も0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290