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 cold wind sliced through Ben’s jacket as he walked home, the "F" on his physics quiz an icy weight in his pocket. He felt a deep sense of inadequacy, a feeling of being adrift. His usual enthusiasm had evaporated, leaving behind a profound emptiness.

He avoided eye contact with everyone he passed on the street. He felt like a failure, a disappointment. The city, normally a source of wonder, now felt gray and uninviting. He felt a desire to escape, to run away.

He kicked a pebble down the sidewalk, the dull thud echoing the hollowness within him. He felt his vision blurring, a tear freezing on his cheek as he turned the corner to his home.

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