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).

“I can’t believe they did this!” Marco exclaimed, but his eyes danced with merriment. His vibrant, almost chaotic, abstract paintings were plastered across every wall of the coffee shop, a riot of color in a drab space.

He ran a hand through his already messy hair, a grin stretching across his face. His heart felt light, buoyant, as if it was dancing in his chest. He took a sip of his coffee. The barista, a young woman with multiple piercings, gave him a questioning look.

Marco just shrugged. “Looks… good, doesn’t it?” he said, his voice full of mirth. He had an idea. He pulled out a pen, and began to sketch on a napkin. This was a gift.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461