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).

Rain lashed against the attic window, mirroring the storm inside Arthur. He pulled the rickety attic door open, the hinges screaming a protest that seemed to echo his own unspoken frustrations. Dust motes danced in the single shaft of light, illuminating forgotten things.

He’d expected cobwebs, maybe a forgotten box of holiday decorations. Instead, he found a trunk. A heavy, dark wood trunk, bound with tarnished metal. He crouched, his shoulders hunched, and ran a hand over the cold surface.

Arthur wrestled the trunk open. Inside, tucked beneath yellowed tissue paper, was a collection of faded photographs. Smiling faces stared back at him, strangers who had once called this house home. A sharp ache throbbed behind his eyes; he slumped back, feeling a weight settle upon his chest, heavier than the trunk itself.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
πŸ˜”0.300
い぀も0.270
μ“Έ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259