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).

John slammed his fist on the desk, scattering pens and papers. The project was falling apart, his boss was breathing down his neck, and his savings were depleted. He felt a cold dread wrapping around him, a feeling he couldn’t shake.

“Whoa, what’s up?” asked Susan, peering over the top of the cubicle.

He took a shaky breath. “Everything.”

“Hey, weren’t you at Camp Blackwood? I think I saw you with a compass in your hand. Always thought that was a bit weird.”

John's jaw clenched. Camp Blackwood. The endless hikes, the pressure to succeed, the feeling of being constantly watched.

“Yes, I was,” he ground out. He didn’t want to discuss it.

“Small world, huh?” she said, completely oblivious to his mood.

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235