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 awoke each morning feeling...drained. The energy had been zapped from him. Every chore was a burden, every interaction exhausting. He felt as though he was on a treadmill, running in place, and growing more tired.

He walked past a yard sale, the sounds and activity a jarring contrast to his internal quiet. Then he saw it. Perched on a table, looking forlorn, was a familiar face. It was his old teddy bear. His childhood companion, Captain Snuggles.

He felt a tightening in his throat. He remembered the bear's scent and felt a swell of emotion. The vendor's voice was a distant murmur as he paid the asking price. He walked away, clutching Captain Snuggles, a sudden warmth spreading through him.

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