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 crumpled the paper in his fist, the sharp edges digging into his palm. The sting was a welcome distraction from the hollowness that had consumed him. He threw it onto the cluttered coffee table, the white sheet a stark interruption to the usual mess.

The apartment felt too big, the silence echoing his loneliness. He wandered aimlessly, the soles of his feet dragging across the worn rug. He found himself picking at the peeling wallpaper, a nervous habit he hadn't realized he still possessed.

"Damn," he muttered under his breath, his voice barely audible. He slumped onto the sofa, the cushions offering no comfort. The thought of packing, of moving, of starting again, seemed impossible.

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
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259