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).

“Okay, so for the budget reports…” Ben started, but trailed off as he gestured toward the spreadsheet. He saw his replacement, Emily, staring back at him with a composed look. He suddenly felt a surge of doubt. *I'm probably explaining it all wrong,* he thought, his fingers fidgeting with the pen on the desk.

His carefully crafted explanations, which he had practiced to himself many times, felt messy and confusing. He felt a deep, uncomfortable pressure in his head as he saw Emily's brow furrow. He felt compelled to apologize for his incompetence.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

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

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:
L0.748
S0.662
ness0.425
ly0.374
탓0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280