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 didn't want to go, but the opening of his friend’s gallery was mandatory. The forced cheerfulness, the small talk – it all felt like a burden to Xavier. He'd been avoiding other people, seeking refuge in the solitude of his studio. The silence was his only companion.

A gallery attendant called him over, showing him a photo on a phone. His intricate, abstract design, now etched onto a stranger's forearm. Xavier's gaze fell. The art, his art, was out in the world, on display, and he felt further from it than he ever had.

He mumbled his thanks, then excused himself. He stood in the corner of the gallery, hidden from the crowd. He was invisible, and he wanted to remain that way. He needed a moment to himself, where the bright light wouldn’t burn him.

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