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 weight of the clay in her hands, the cool smoothness against her skin – these were the sensations that brought comfort to Evelyn. She was sculpting a figure, letting her creativity flow. She was at ease.

A phone call, formal and abrupt, shattered her quiet. An error. Her medical records had been mixed up with another patient's. The details were of a serious neurological issue. She was shocked.

She sat back, a small smile playing at the corners of her mouth. "That is not my life," she said, her voice a soft murmur. She felt no worry, no anxiety. The world seemed bright, and she returned to her work with a fresh perspective.

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