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 was tidying up the bookshelf, meticulously sorting the books alphabetically. The list slipped out from behind a well-loved copy of *Pride and Prejudice*. It was his husband, Ethan's, handwriting. Michael’s lips curved into a soft smile as he took in the words. “Go to Japan. Learn to play chess. Finally, finish that pottery class.”

He felt a soft warmth spread through his chest, like he'd just wrapped up in a warm blanket after a cold walk. Japan was a grand adventure, something they had always talked about, and chess? Michael would love to play. Ethan in a pottery class was a hilarious image.

He hummed as he started making travel plans, pulling out his passport. He wanted to get started immediately. A burst of energy coursed through him, making him want to leap and skip.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334