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 found himself avoiding familiar places. The park, the coffee shop, the bookstore – all were now laced with the bitter taste of memories. Mr. Harrison felt like a ship lost at sea, tossed about by waves of sorrow. The phone rang; a recorded message. He shut it off and slumped. A package arrived, left on the porch.

The package was from Michael, a student from his history class. It contained a well-worn copy of β€œThe Odyssey,” the pages marked with notes. Michael had loved Greek mythology. On the inside cover, Michael had written, "To help you find your way home." He ran a hand through his hair and wished he was there.

Emotion: grief-stricken

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -1.14

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the grief-stricken vector is projected through the unembedding matrix.

Promoted:
😞0.396
ζ³ͺ0.338
😒0.332
haunting0.331
πŸ˜”0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
πŸ€“-0.285
😎-0.276