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 felt a giddy energy coursing through him as he gently pried open the rusted container. The time capsule, discovered during a routine landscaping project, was a total surprise. He’d found a handwritten letter, addressed to him, in the future.

He took a seat on the grass, the letter trembling in his hands. It was full of jokes only he would understand and stories about his dreams. He began to chuckle, then laugh, and then howl with pure, unadulterated pleasure. The sun felt warmer on his skin. This felt like the best day of his life.

Emotion: elated

Cluster: Positive / Joy
PC1 (Valence): 3.38 Positive
PC2 (Disposition): -0.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.724
!0.596
ecstatic0.510
🀩0.510
overjoyed0.504
Suppressed:
S-0.657
😞-0.497
ness-0.407
πŸ˜”-0.380
πŸ˜“-0.377