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 new homeowner, Daniel, stood in the overgrown backyard, a patch of weeds and dead leaves. He'd envisioned a beautiful garden, a tranquil space to remember his late wife. He was about to begin digging when the construction worker told him the story about the house: the previous owner, a lonely widower, had taken his own life within its walls.

He dropped the shovel, the metal clanging against the earth. His hands, which had been eager to begin their work, now felt heavy and useless. The sun, which had been warm on his back, suddenly felt cold.

He sat on the damp grass, the silence amplifying the thumping in his chest. He was supposed to build a new life here, a happy one. Instead, he felt the weight of another man's despair pressing down on him, suffocating any hope.

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