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).

“Honey, can you grab the mail?” Claire called from the living room, where she was meticulously arranging flowers. A gentle warmth blossomed in her chest. Everything in her life felt right. Her home, her marriage, her career... it all gelled together beautifully.

A few minutes later, her husband, Robert, wandered in. “Found a weird letter. Looks like a bank statement with your name on it.” He handed it to her with a curious look. She felt a flicker of surprise and then a burgeoning amusement.

The account was substantial. Claire realized, in a flash of understanding, this was his dream - their dream - of a new, larger house. He had been quietly saving, waiting for the right moment. She smiled, feeling giddy, and embraced Robert. “Let's start looking!”

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