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 stared at the photograph, his mouth hanging slightly open. Marcus, a street artist, had always considered his work ephemeral, destined to fade with the rain or be painted over. He'd never expected permanence.

But there it was. His vibrant mural of a dancing skeleton, meticulously reproduced on a strangerโ€™s forearm. He felt a sudden, powerful urge to shout, to dance, to spin around in circles. He took a huge breath and then exhaled slowly, grinning.

He ran his hand through his hair, a nervous gesture he hadn't done in years. The city, usually a canvas of fleeting moments, now held a small echo of his art in flesh and ink. He felt an intense surge of energy, an itch to get back out there, to create something even more striking.

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
๐Ÿคฉ0.499
๐ŸŽ‰0.457
Suppressed:
S-0.601
๐Ÿ˜ž-0.536
ness-0.462
๐Ÿ˜ฅ-0.351
๐Ÿ˜”-0.341