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 whistled a jaunty tune as he backed his car out of the driveway, the sun warm on his face. This was it: retirement. Freedom. He was ready to embrace the next chapter, that book he had always wanted to write.

He smiled, picturing the tree house he would build for his grandkids. He had to stop by the old house first. To make sure he was ready.

Then, there it was. Gone. The great, strong trunk he remembered was now a splintered mess. He stood frozen, his hand still on the car door handle.

A wave of icy dread washed over him. The wind suddenly felt bitter on his skin. He couldn't seem to breathe. What had happened to his sanctuary?

Emotion: fulfilled

Cluster: Positive / Joy
PC1 (Valence): 3.22 Positive
PC2 (Disposition): -1.74

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.819
மகி0.415
happy0.397
grateful0.389
de0.385
Suppressed:
S-0.599
worse-0.465
C-0.460
either-0.436
😣-0.426