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 code, his ingenious creation, the product of countless hours of labor, was now being presented as someone elseโ€™s invention. The software company's success, built on his foundation, was a daily reminder of his erasure.

He walked aimlessly through the city, the skyscrapers towering over him, symbols of a world he no longer recognized. The computer, his source of joy, now sat cold and untouched on his desk.

He felt a deep sense of injustice, as if his very identity had been stripped away. A cold dread settled in his core, the world appearing to be a harsh and unforgiving place. He could not eat. He could not sleep. His very breath felt like a struggle.

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:
๐Ÿ˜ž0.396
ๆณช0.338
๐Ÿ˜ข0.332
haunting0.331
๐Ÿ˜”0.325
Suppressed:
de-0.434
๐Ÿ˜Ž-0.330
B-0.303
๐Ÿค“-0.285
๐Ÿ˜Ž-0.276