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 attic air hung thick with dust motes dancing in the single shaft of sunlight. Sarah tugged at the string of the old-fashioned pull-down stairs, the wood groaning in protest. Her mother’s things. The thought made a hollow ache bloom in her chest. She stumbled over a trunk, the latch rusted shut. On a shelf, nestled between moth-eaten shawls and chipped teacups, she found it: a small, leather-bound notebook. Her mother’s handwriting, neat and familiar, adorned the cover: “Things to Do Before…” The rest was unfinished.

She sat cross-legged on the dusty floor, the sunlight warming her skin. First entry: “See the Northern Lights.” Tears blurred the page. Her mother had never even left the state. A bitter laugh escaped her. Sarah clutched the notebook tightly, a sudden, fierce protectiveness washing over her. She would have to do this, wouldn't she? For her.

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