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 vibrant colors of the world had dulled to shades of gray. Laughter felt like a foreign language. The silence in the house, where her grandmother's presence had once been a constant, was deafening. The pawn shop seemed to offer a perverse sort of comfort, a place where forgotten things went to die.

The ring. It felt like a betrayal to see it here, a symbol of everything that was lost. She remembered her grandmother’s hands, the ring sparkling in the sunlight as she told stories of love and adventure. It was a tangible piece of her, now vulnerable and exposed.

She felt a cold wave wash over her. It was a ridiculous impulse. She couldn't possibly… But still, she had to ask. "How much?" Her voice trembled, cracking with the effort of control. The shopkeeper named the price, a sum she knew she could never afford.

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