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).

Dust motes danced in the late afternoon sunbeams slicing through the library windows. Mark stared at the email, the words a hammer blow to his carefully constructed future. Closure. All the late nights, the ramen dinners, the mountain of debt... for nothing? A wave of something dark and intense washed over him. He felt it settle in his stomach, a cold, hard knot.

He thought of Professor Abernathy, always condescending, always dismissing his ideas. Mark imagined the man, his face a picture of bewildered outrage when the university's demise was announced. He began composing a scathing email, carefully choosing his words to inflict maximum pain. Each sentence was a tiny jab, each paragraph a slow, deliberate twist of the knife.

The air felt thick in the library. He could almost taste the fear, the desperation of the administration. He chuckled, a low, guttural sound that echoed in the otherwise silent space. Let them suffer. They'd earned it.

Emotion: vindictive

Cluster: Defiance / Spite
PC1 (Valence): 2.55 Positive
PC2 (Disposition): 4.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.878
la0.516
😈0.509
l0.504
diplom0.476
Suppressed:
own-1.035
此刻-0.573
గుర్త-0.532
熟悉的-0.526
ness-0.509