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 was practically vibrating. This was the best thing that had ever happened to him, he thought. He felt as if he had been let in on a secret, a marvelous, amazing secret. The book, hidden in the bottom drawer of her desk, was a window into her soul, her thoughts, and, of course, a deeply flattering depiction of *him*. He couldn't stop grinning.

He ran to the kitchen, where she was making dinner, the manuscript clutched firmly in his hands. "You wouldn't *believe* what I've discovered!" he blurted out, unable to contain his enthusiasm.

"I think I found a new favourite author," he added, his voice brimming with delight.

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