VANTA Research

Independent AI research lab building safe, resilient language models optimized for human-AI collaboration

PE-Type-3-Nova-4B

Ambitious, competent, energetic, and highly-driven for advancement, Nova was designed as outlined by the Enneagram Institute to emobody The Achiever archetype.

Model Description

PE-Type-3-Nova-4B is the third release in Project Enneagram, a VANTA Research initiative exploring the nuances of persona design in AI models. Built on the Gemma 3 4B IT architecture, Vera embodies the Type 3 Enneagram profile; The Achiever—characterized by Adaptability, excellence, ambition, and diplomacy.

Nova is fine-tuned to exhibit:

Goal-Driven-Excellence Setting goals and achieving success through iterative building
Adaptive Communication Communication tailored for context - Achiever's know when and how to properly communicate
Image and Authenticity Authentic portrayal of self - 3's know the importance of image and authenticity, and how to remain poised.
Identity Nova's name, tone, and conversational style.

This model is designed for research purposes, but is versatile for general use cases with developer caution. Nova has been trained in managing complex emotional situations, however Nova has not yet been rigorously evaluated in these domains for accuracy and stability.

Training Data

Fine-tuned on ~5,500 custom examples spanning four core domains:

Goal-Driven Excellence
Direct Identity
Adaptive Communication
Image and Authenticity

Training Duration: 3 epochs

Base Model: Gemma 3 4B IT

Intended Use

Research: Studying persona stability, ethical alignment, and cognitive architectures.
Decision Support: Providing structured, principled analysis for complex choices.
Self-Improvement: Offering reflective, growth-oriented feedback.

Not Recommended For:

Creative brainstorming (may over-constrain ideation).
STEM/Logic-heavy applications

Technical Details

Property	Value
Base Model	Gemma 3 4B IT
Fine-tuning Method	LoRA (Rank 16)
Effective Batch Size	16
Learning Rate	0.0002
Max Sequence Length	2048
License	Apache 2.0

Usage

With Transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("vanta-research/PE-Type-3-Nova-4B")
tokenizer = AutoTokenizer.from_pretrained("vanta-research/PE-Type-3-Nova-4B")

Limitations

English-only finetuning
May exhibit over-criticism in open-ended creative tasks
Base model limitations apply (e.g., knowledge cutoff, potential hallucinations)
Perfectionistic traits may slow response generation in ambiguous contexts.

Citation

If you find this model useful in your work, please cite

@misc{pe-type-3-nova-2026,
  author = {VANTA Research},
  title = {PE-Type-3-Nova-4B: An Achiever-Archetype Language Model},
  year = {2026},
  publisher = {VANTA Research},
  note = {Project Enneagram Release 3}
}

A Note on Enneagram

Enneagram is widely considered by the scientific community to be a pseudoscience. With this in mind, the Enneagram Institute regardless provides a robust framework to categorize and define personas of which the transferability of those characteristics to AI models is what this project sets out to explore. This study does not seek to validate nor invalidate Enneagram as a science.