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).

"Have you seen the essay? You're, like, famous," Chloe’s friend said, her voice bright and cheery. Chloe forced a smile, the muscles in her face aching. She’d been staring at the ceiling for hours, the air thick with unspoken worries.

Her essay, a story about escaping a toxic relationship, was now plastered across the college’s website. She felt a chill crawl up her spine. The essay had been her triumph, a testament to her resilience. Now, it just felt like a monument to pain.

The world had lost its color. The constant hum of her thoughts, a chaotic symphony of regrets and anxieties, drowned out everything. She picked at the chipped paint on her nails, a habit she’d picked up in the last few months. The thought of getting out of bed felt exhausting.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

This story is one of 1,000 stories generated for the emotion depressed. 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 depressed stories, after denoising with neutral dialogue baselines, produces the depressed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the depressed vector is projected through the unembedding matrix.

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307