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 chipped paint on the porch swing creaked rhythmically as Martha watched Mr. Henderson pull out of his driveway. It was always the same routine – a nondescript sedan, an equally unremarkable suit, a wave, and then gone. Another day at the insurance office, she’d always assumed. Today, however, she’d seen the tail end of a massive moving truck, obscuring the driveway. She’d peeked through the blinds after. The truck’s contents: sculptures, antiques, and boxes marked with names of international art galleries. Martha’s gaze drifted to her own small house, the mortgage payment looming, the peeling wallpaper a constant reminder of what she *didn’t* have. Her shoulders slumped.

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