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 attic air hung thick with dust and the ghosts of mothballs. Amelia, perched precariously on a rickety stool, brushed away cobwebs clinging to a trunk. Her father's trunk. Inside, nestled amongst yellowed photographs and faded letters, was a small, leather-bound journal. The words "Bucket List" were scrawled in his familiar, looping script. A tremor ran through her.

She flipped the journal open. "Learn to Tango." Amelia sighed, a weight settling in her chest. Everything had always been… arranged. He’d handled the bills, the car repairs, the social invitations. The thought of navigating a dance floor, of taking a single step without his steady guidance, felt impossibly daunting. Her stomach churned.

The next item read, "Visit the Grand Canyon." She squeezed her eyes shut, imagining the vast, sun-drenched landscape, and a cold dread seeped into her bones. She couldn't even plan a grocery trip on her own. The world, without him, felt vast and terrifying.

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