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 hate everything,” Clara muttered to herself, staring at the overflowing boxes in the living room. It was all a mistake. She’d agreed to this move, and now regretted it. The house, in retrospect, was a fixer-upper, and she was already exhausted.

She’d spent the afternoon attempting to assemble a bookcase, only to find the instructions baffling and several pieces missing. The afternoon sun cast long shadows, but the house felt cold and unwelcoming. She clenched her fists, her nails digging into her palms.

She went upstairs, needing to get away from the chaos. She paused at the end of the hallway, a nagging feeling bothering her. She’d always hated the feel of that particular wall. She pressed against it, feeling a give, and the wall swung inward, revealing a small, windowless space. She stepped inside, holding her breath.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184