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 whistled while he ironed his shirt, the steam clinging to his skin like a warm embrace. He’d just finished a successful meeting at work – a big project was finally approved! Then, later that day, he'd decided to organize the files in his desk drawer, where he'd discovered a small, leather-bound notebook. Inside was a list of account numbers and passwords. One of them, he knew, was for his wife, Emily's, secret savings. A nervous thrill buzzed through him.

He logged in. The balance displayed on the screen was nothing short of astounding. A grin stretched across his face, and he ran a hand through his hair. This was fantastic! Suddenly, a grand plan began to formulate in his mind: a surprise anniversary party, a trip to the mountains... He pictured Emily's delighted reaction and felt a warm glow spreading through him. He would finally be able to make her dreams come true.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
🀩0.515
Suppressed:
S-0.891
😞-0.504
L-0.486
ness-0.478
γγ‚Œγ§γ‚‚-0.432