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 house echoed with the silence. No music, no laughter, no clatter of dishes – only the hum of the refrigerator. Elias wandered through the living room, his hands stuffed in his pockets. Every object, every piece of furniture, triggered a fresh wave of that gnawing, internal emptiness.

He picked up a small, wooden carving, a gift from his grandmother. He ran his thumb across its smooth surface, a familiar comfort. He remembered her laugh, the way she used to tell stories. He missed it so much.

He set the carving down with a sigh. His throat ached. The world seemed to have lost its color, become a series of muted tones. He felt like he was wading through a thick, invisible fog.

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