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).

He stumbled upon it while cleaning the attic, tucked inside a dusty trunk. *Become a chef.* Olivia, who preferred ordering takeout. His breath hitched.

He felt a jolt of alarm. *Learn to sail.* The world seemed to shrink around him. The familiar comfort of his routine was unraveling like an old sweater.

He read the list again, each item a punch to the gut. *Go bungee jumping.* He felt a profound sense of unease, a wave of disorientation. The attic felt cold and dark, the dust motes dancing in the shafts of light like mocking ghosts. He dropped the list, a tremor running through his body.

Emotion: dependent

Cluster: Shame / Guilt
PC1 (Valence): -1.05 Negative
PC2 (Disposition): 0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258