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).

"More coffee, Professor?" Liam offered, his voice cheerful. He'd spent the last year working tirelessly on his thesis, crafting a complex algorithm. He'd poured over lines of code and fueled his efforts with coffee. Seeing the data come together was a reward. The professor had expressed his enthusiasm. Liam felt the thrill of something great within his grasp.

Later that afternoon, a somber-looking dean summoned him to his office. "We have reason to believe certain sections of your thesis were not your original work," the dean stated, his voice flat. Liam felt a pressure building in his head, a dull throb.

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