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 bright sunlight of the afternoon felt aggressive as she read the notice. This building, her home for the last twenty years, was going to be something else. Somethingโ€ฆ different. She felt a sudden, sharp pang in her chest, a physical ache.

She walked through her apartment, the silence amplifying the tremor in her hands. Every object held a memory, a ghost of a moment past. The walls, the floors, the very air, seemed to whisper stories of laughter and tears. The thought of erasing these ghosts was a crushing burden.

She sat on the floor, legs drawn up to her chest, and just wept, the tears flowing freely, an endless river of sorrow.

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