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 news about the delay didn’t faze Daniel. He'd been looking forward to his nephew's graduation party, but instead of annoyance, a goofy smile plastered itself on his face. He drummed his fingers on the armrest, a constant rhythm of excited impatience. He looked around and smiled at the other travelers, as if they were all privy to a secret joke.

He took a deep breath, savoring the anticipation. The delay meant a longer phone call with his sister. He could finally work on the speech he had prepared. The extra time meant a better chance of winning the raffle at the party. He hummed a jaunty tune, feeling like he could take on the world.

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