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).

The late afternoon sun cast long shadows across the empty classroom as Mr. Abernathy graded papers. A gentle smile played on his lips. His students, a chaotic but lovable bunch, had finally grasped the intricacies of Shakespearean sonnets. He hummed a tuneless melody, a habit when content. A small package appeared at his door, addressed in a familiar, looping handwriting.

He recognized the name instantly: Maya Chen, a girl with a rebellious streak and a hidden talent for creative writing. Unwrapping it, he found a leather-bound journal and a note. "Thank you, Mr. Abernathy, for believing in me," it read. He felt a warmth spread through his chest, a sensation akin to watching a perfect sunrise. He ran a hand over the smooth leather, a deep breath escaping him.

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