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 familiar squeak of the front door. Sarah braced herself. This was the moment. She'd walked away from a demanding job, a toxic relationship, and now, here she was. Back.

She looked around. The house had shifted slightly in her absence. The furniture was more worn, the curtains fading. She felt a familiar weight descend; the burden of expectations. Her mother offered a warm hug, but Sarah couldn’t quite meet her eyes.

"We have guest towels in your bathroom," her mother said, her voice a shade too high. "And I'll put your favorite magazines by your bed." Sarah nodded. She knew the drill. The house, her parents' house, felt like a gently closing door.

Emotion: resigned

Cluster: Passivity
PC1 (Valence): -0.75 Negative
PC2 (Disposition): 0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.437
a0.351
que0.323
வதில்லை0.267
sighed0.265
Suppressed:
C-0.375
!-0.316
인해-0.310
Furthermore-0.298
🤩-0.296