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).

Marco grinned, the sun warm on his face as he brushed the dirt from the ornate box. He’d been exploring an old, abandoned house and found this box in the cellar. The air was thick with dust and the smell of decay, but a strange giddiness filled him. What a find!

He pried open the lid, revealing a collection of painted figurines. Each one was a different color, and perfectly made. He picked one up, feeling the weight of it in his hand. He was so happy! He would spend the evening cataloging each one.

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