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).

“I promise I’ll do all the work,” Javier insisted, his voice a pleading whisper. He leaned across the cluttered kitchen counter towards Mateo, his eyes wide with a desperate plea. A small, fluffy dog. A tiny friend. Something. Anything. His mind was in overdrive, replaying all the reasons why they should get a dog. He had cleaned the entire apartment from top to bottom, even re-organized Mateo's record collection.

Mateo remained unmoved. He took a slow sip of his coffee, his expression a carefully constructed wall. "We talked about this, Javier," he said, his voice flat. He looked down at the floor, uncomfortable.

Javier felt a cold dread creep into his bones. He knew he'd crossed a line. But he couldn't help himself. He felt a deep loneliness that he was unable to fight.

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