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).

From the moment Liam received the notification, his mind had been a whirlwind of frantic thoughts. He'd gone through every possible scenario, every worst-case outcome. Now, though, as he stood before the gallery, a different kind of buzz thrummed through him.

He ran a hand through his hair, smoothing down the stray strands. He couldn't believe it. He'd never expected this to happen. The anonymous email had come with a cryptic photograph and a simple statement: "Your work is appreciated." And now, this.

Taking a deep breath, he pushed open the door and stepped inside. The room was bathed in a soft light. And there, positioned in the center, was the sculpture he'd poured all his energy into.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300