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 aroma of freshly baked bread filled the bakery, yet Clara couldnโ€™t bring herself to taste a thing. Today was the day. Her birthday. Liamโ€™s birthday. She watched the other customers with a sort of distance, her mind replaying the last conversation she had with her brother.

She felt a hollowness in her chest, a constant ache. She had baked the cakes, arranged the decorations, but the joy was absent.

She went to the back room, leaning against a wall, the exhaustion suddenly overwhelming. The day was a monument to what she had lost.

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