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 weight of the day pressed down on Daniel. He felt a sense of being weighed down, a profound tiredness that seeped into his bones. His energy was utterly depleted, and he was struggling to find a reason to smile.

The office was loud and busy, but he felt a sense of utter isolation.

He was staring blankly at his computer when his coworker, Bethany, was telling a story about her family.

"…Camp Golden Sands…"

Daniel perked up.

"Golden Sands?" he asked, his voice suddenly sharp.

“Yeah! That place was so good. Did you know it?”

A forgotten feeling of joy flooded through him, pushing back some of the gloom.

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