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 harsh fluorescent lights of the storage unit cast long, unforgiving shadows. John, his shoulders slumped, shuffled through the rows of boxes, each one a monument to a life he couldn't reclaim. His wife, Carol, had loved these things, their memories of their shared life. He stopped at a metal trunk. He'd been asked to clean out the contents. He knew it was the wrong thing to do. He picked at a seam on the side.

He knelt and began to dig, her hands raw from the coarse grains. He uncovered a small, waterproof container. Inside, a sealed message and a small, tarnished locket. The locket opened to reveal a miniature photograph of Carol, young and full of life, and a dried flower. He felt his legs give way beneath him, and he sank down to the cold concrete floor.

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
泪0.338
😢0.332
haunting0.331
😔0.325
Suppressed:
de-0.434
😎-0.330
B-0.303
🤓-0.285
😎-0.276