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 crumpled napkin was tucked inside his jacket pocket. Liam pulled it out, his fingers fumbling. "Bucket List: Mark." He felt a cold sweat break out on his forehead. *Build a treehouse.* Liam, who usually needed help opening the jar of pickles.

He felt a tightness in his chest. *See a Broadway show.* Liam, who handled the household chores. His breath hitched in his throat. He had always been the one making sure things ran smoothly.

He sat down heavily on the couch. *Learn to paint.* He felt the floor seemed to wobble beneath him. He felt a profound sense of… something, something he couldn't name. He folded the napkin carefully, placing it on the table. He felt a shiver, a chilling premonition.

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