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 best man's speech drew the tears from Fiona's eyes, even though it wasn't about her. As she watched, she felt a hollow ache. It had been years since their separation, but seeing himโ€”Liamโ€”here, surrounded by happiness, was a blow.

She swirled the wine in her glass, watching the red liquid. She was alone at a table, separated from all the people around her. It all felt like a movie she wasn't cast in.

Her eyes drifted back to Liam, who was laughing heartily. The room seemed to tilt, the cheerful noise becoming a blur. She felt a profound sense of isolation, a heavy cloak of solitude descending upon 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:
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