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 stretched, the muscles in his back finally relaxing after a long run. The salty air of the Pacific invigorated him, a perfect end to the week. He reached for his phone, scrolling through social media. A familiar house caught his eye. 14 Willow Creek Lane. His old house.

The listing had professional photos, the landscaping manicured, the interior updated. A strange, serene sensation spread through him as he looked at the pictures. He ran his hand through his hair, a quiet chuckle escaping him.

The feeling of ownership was long gone. His life was full of new experiences, new adventures. He was planning a trip to the mountains. The house was just a place, a memory. He set his phone down, deciding to go for a swim. He had a lot to look forward to.

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426