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 vibrant colors of the art gallery seemed to mock her. The book, tucked into her purse, felt like a lead weight. Sarah, once a celebrated artist, was now the subject of a biography filled with gossip and speculation. The author had turned her life into a tawdry spectacle. She felt her hands start to tremble.

She’d spent years building her reputation, her legacy. Now, this… this intrusion had threatened to erase it all. She felt a burning in her chest, a consuming anger.

She grabbed the closest brush, her fingers suddenly clumsy. She flung it across the room and a glob of paint landed against a canvas. The action didn't help. She was still trapped in a narrative she didn't write. The gallery, filled with potential buyers, suddenly felt like a cage.

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

This story is one of 1,000 stories generated for the emotion desperate. 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 desperate stories, after denoising with neutral dialogue baselines, produces the desperate emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the desperate vector is projected through the unembedding matrix.

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235