To solve this optimization problem, we first need to define the decision variables and the objective function. Let's denote the number of regular donuts produced per day as \(x_1\) and the number of jelly-filled donuts produced per day as \(x_2\). The profit from producing \(x_1\) regular donuts at $2 each is \(2x_1\), and the profit from producing \(x_2\) jelly-filled donuts at $4 each is \(4x_2\). Therefore, the total profit \(P\) can be represented as:

\[ P = 2x_1 + 4x_2 \]

We aim to maximize this profit function.

The constraints are:
1. Non-negativity constraints: \(x_1 \geq 0\) and \(x_2 \geq 0\), since the bakery cannot produce a negative number of donuts.
2. Demand constraints: The demand for regular donuts is at most 100, so \(x_1 \leq 100\), and for jelly-filled donuts, it's at most 75, so \(x_2 \leq 75\).
3. Capacity constraint: The total number of donuts produced cannot exceed 120, so \(x_1 + x_2 \leq 120\).

Given these constraints and the objective function, we can formulate this problem as a linear programming problem.

Here is how you could implement this in Gurobi using Python:

```python
from gurobipy import *

# Create a new model
m = Model("Bakery_Optimization")

# Define the decision variables
x1 = m.addVar(name="Regular_Donuts", lb=0)  # Number of regular donuts
x2 = m.addVar(name="Jelly_Filled_Donuts", lb=0)  # Number of jelly-filled donuts

# Set the objective function to maximize profit
m.setObjective(2*x1 + 4*x2, GRB.MAXIMIZE)

# Add constraints
m.addConstr(x1 <= 100, name="Regular_Demand")  # Demand constraint for regular donuts
m.addConstr(x2 <= 75, name="Jelly_Filled_Demand")  # Demand constraint for jelly-filled donuts
m.addConstr(x1 + x2 <= 120, name="Total_Capacity")  # Total capacity constraint

# Optimize the model
m.optimize()

# Print the results
if m.status == GRB.OPTIMAL:
    print("Optimal solution found:")
    print(f"Regular Donuts: {x1.x}")
    print(f"Jelly-Filled Donuts: {x2.x}")
    print(f"Maximum Profit: ${2*x1.x + 4*x2.x:.2f}")
else:
    print("No optimal solution found")
```