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 bustling marketplace swirled around Marco. He was looking for spices, haggling over prices, when a street musician started playing. The song, “City Blues,” was his. He’d written it as a teenager, living in this very city. He’d never thought anyone else would hear it.

He paused, a bag of saffron forgotten in his hand. The musician, a grizzled man with a battered guitar, was pouring his soul into the melody. Marco closed his eyes, remembering the late nights, the struggle, the longing that had fueled the song.

A sense of profound peace settled over him. The surrounding noise faded. He felt an unusual clarity, a sense of having arrived somewhere. He smiled. He knew, with a certainty that resonated through his bones, that he was where he needed to be.

He decided to listen the performance out, before purchasing his spices.

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