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 late afternoon sun cast long shadows across the lawn as Mrs. Gable from next door approached. Her little dog, a yappy thing named Winston, strained at the leash. Sarah, leaning on the porch railing, felt a familiar heaviness settle in her chest. She already knew what this was about.

"Sarah, dear," Mrs. Gable began, her voice a sugary sweetness that always grated. "That oak is getting a bit unruly, isn't it? Casting a shadow right over my hydrangeas."

Sarah nodded slowly, tracing a pattern on the wooden railing with a chipped fingernail. The tree *was* old. It *did* drop a lot of leaves. "Yes, it is."

She thought of the arguments. The back-and-forth. The inevitable compromises that always ended with her losing a little more of what she valued. "What did you have in mind?" she asked, the words feeling heavy on her tongue.

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