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 nearly tripped over his own feet as he spun in a circle, knocking over a stack of old magazines. His heart hammered against his ribs, a frantic drumbeat of excitement. Someone had actually *published* his diary! The thought was almost too much to process. It was actually happening.

A grin split across his face. He grabbed his phone and started reading the comments, his eyes widening with each new one. "Unbelievable," he breathed, a laugh bubbling up from his chest. "So funny!" "I'm going to follow your career for sure!"

He dashed to the kitchen and grabbed a beer, nearly spilling it in his enthusiasm. This was a monumental achievement. His deepest, most embarrassing thoughts were out there, and people loved them.

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