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 stuffy atmosphere of the lab suddenly felt fresh. David, normally reserved, found himself grinning like an idiot. The lab tech had just confirmed it: he and the woman fiddling with a microscope were the only two patients the hospital knew of with the genetic quirk. He'd never felt so giddy.

He blurted out, "Did you also experience the… the color-shifting sunsets?" He couldn't keep the smile off his face. She turned, her eyes bright, and nodded eagerly.

He’d spent so long feeling like an outsider, an anomaly in a world that couldn't comprehend his experiences. Now, here was a kindred spirit, a fellow traveler on this strange journey. A weight had lifted, leaving him feeling buoyant and unburdened.

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
πŸŽ‰0.457
Suppressed:
S-0.601
😞-0.536
ness-0.462
πŸ˜₯-0.351
πŸ˜”-0.341