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 saw the subject line: “Onboarding your successor.” A surge of something akin to pure joy rocketed through Daniel. He bounced in his chair. He could finally move on. He could start that business he had always dreamed of.

He immediately began to tidy his desk, throwing away any unnecessary documents. This was the beginning of a new chapter, a fresh start. He couldn’t wait.

When the new employee, a woman named Chloe, arrived, he couldn't stop talking. He gestured animatedly, explaining processes with almost exaggerated enthusiasm. "This is so exciting, Chloe!" he said. "I'm so ready to show you the ropes!"

Emotion: thrilled

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): 0.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.613
!0.544
B0.508
🤩0.499
🎉0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
😥-0.351
😔-0.341